© 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. 107558
    Prev
    Next
    INDEX
    Explanations

    SG variants

    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_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
    Stab
    -0.72
     Huey
    -0.72
     verständ
    -0.71
    Jude
    -0.70
    hue
    -0.68
    ssm
    -0.66
     farlo
    -0.64
     服
    -0.64
    Rude
    -0.64
    chon
    -0.63
    POSITIVE LOGITS
     SG
    5.41
    SG
    5.03
    sg
    4.56
     sg
    4.47
    Sg
    3.48
     Sg
    3.34
    SGD
    2.73
     SGD
    2.72
    SGS
    2.61
     SGS
    2.56
    Activations Density 0.036%

    No Known Activations