© 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. 34-GEMMASCOPE-RES-131K
    7. 108506
    Prev
    Next
    INDEX
    Explanations

    `//===` starts

    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
    '])->
    -0.82
    tega
    -0.76
    {{-
    -0.72
     Sart
    -0.72
    BLM
    -0.71
    àn
    -0.71
    존
    -0.70
    isch
    -0.69
     subversion
    -0.69
     Brum
    -0.68
    POSITIVE LOGITS
    bisk
    0.65
     helicopter
    0.65
     parking
    0.64
     Lonely
    0.64
    triangleright
    0.63
    Kib
    0.62
     eternity
    0.62
     צילום
    0.62
     Parking
    0.61
     AG
    0.59
    Activations Density 0.097%

    No Known Activations