© 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. 116248
    Prev
    Next
    INDEX
    Explanations

    time stamps and case numbers

    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
     just
    -1.20
     only
    -1.18
     each
    -1.07
     проє
    -1.04
     every
    -0.99
     would
    -0.98
     throughout
    -0.96
    ﾁ
    -0.93
     things
    -0.92
    غذ
    -0.91
    POSITIVE LOGITS
    phous
    0.90
     Sopho
    0.90
    uel
    0.89
    »،
    0.89
    provide
    0.89
    Ali
    0.88
    dy
    0.84
    k
    0.84
    Z
    0.83
    »
    0.82
    Activations Density 0.050%

    No Known Activations