© 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. 99101
    Prev
    Next
    INDEX
    Explanations

    describing states of being

    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
    BRARY
    -0.95
    блі
    -0.91
     relativamente
    -0.87
     destro
    -0.82
     FUCK
    -0.82
     thingy
    -0.81
     Muddy
    -0.81
     fellow
    -0.81
     POOR
    -0.81
    sizlik
    -0.80
    POSITIVE LOGITS
     such
    1.48
     a
    1.21
    Such
    1.17
     an
    1.01
     Such
    0.94
     dramatic
    0.94
     drama
    0.88
     biggest
    0.86
    such
    0.84
     такой
    0.83
    Activations Density 0.034%

    No Known Activations