© 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. 103564
    Prev
    Next
    INDEX
    Explanations

    number or category, then description

    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
     might
    -1.16
     some
    -1.09
     or
    -1.09
     seemed
    -1.05
     when
    -1.02
     if
    -1.02
     on
    -1.01
     who
    -0.96
     focusing
    -0.94
     prevent
    -0.94
    POSITIVE LOGITS
    rée
    1.23
     corriger
    1.13
    atics
    1.09
    ishing
    1.09
    enie
    1.06
    atization
    1.06
    discovered
    1.04
    𝕒
    1.04
    cination
    1.03
    lization
    1.02
    Activations Density 0.002%

    No Known Activations