© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23532
    Prev
    Next
    INDEX
    Explanations

    iterative inversion reconstruction

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron selectively activates on complex, domain‐specific technical terms and method names (e.g. “unfolding,” “unscrambling,” “spatio‐temporal cortical source imaging,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     POND
    -0.79
     caseros
    -0.72
     raz
    -0.69
     polypropylene
    -0.68
    resizable
    -0.68
     exaggerating
    -0.67
    Betting
    -0.66
     Lun
    -0.66
     interpolated
    -0.66
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.65
    POSITIVE LOGITS
     inverse
    2.64
     inversion
    2.48
    inverse
    2.44
    Inverse
    2.16
     Inverse
    2.06
     Inversion
    2.05
    inversion
    1.93
     inver
    1.91
     invert
    1.73
     invers
    1.57
    Activations Density 0.087%

    No Known Activations