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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66899
    Prev
    Next
    INDEX
    Explanations

    current or proposed states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    brtc
    -1.77
     וכן
    -1.59
     dépens
    -1.56
    continues
    -1.55
    wants
    -1.54
    attended
    -1.48
    ("")]
    -1.47
    launched
    -1.47
    begins
    -1.45
     berbagai
    -1.45
    POSITIVE LOGITS
     is
    1.95
     offering
    1.52
     thing
    1.52
     will
    1.49
     has
    1.48
     result
    1.45
    '
    1.44
     experience
    1.38
     isn
    1.36
    2
    1.35
    Activations Density 0.096%

    No Known Activations