Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12101
    Prev
    Next
    INDEX
    Explanations

    ch or Ch prefixes

    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_22/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
    </h3>
    -3.02
    </sub>
    -2.44
    ו
    -2.34
     was
    -2.33
     curiously
    -2.20
     tragically
    -2.19
    u
    -2.17
    </strong>
    -2.17
     実例
    -2.13
    確認ください
    -2.09
    POSITIVE LOGITS
    </b>
    3.06
    '
    2.61
    ylase
    2.31
     were
    2.30
    $,
    2.30
     I
    2.25
    cherichia
    2.22
    ',
    2.19
    ".
    2.13
    ский
    2.09
    Activations Density 0.053%

    No Known Activations