© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118973
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     on
    -1.19
     after
    -1.14
     when
    -1.13
     both
    -1.08
     at
    -1.07
     cleverly
    -1.05
     first
    -1.02
     protect
    -1.00
     using
    -1.00
     an
    -1.00
    POSITIVE LOGITS
     Dinas
    1.10
     วิ
    1.05
     素描
    0.98
    ystemen
    0.98
     memória
    0.96
    OW
    0.95
     Claus
    0.94
    xffff
    0.94
    jaan
    0.93
     extravag
    0.93
    Activations Density 0.009%

    No Known Activations