© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110446
    Prev
    Next
    INDEX
    Explanations

    month names

    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
     Fig
    -1.00
     Figs
    -0.99
    栏目
    -0.80
     Eq
    -0.78
    Figs
    -0.73
    ßt
    -0.73
     btn
    -0.73
    ⠓
    -0.70
    Btn
    -0.69
    alignSelf
    -0.69
    POSITIVE LOGITS
     September
    1.73
     January
    1.73
     October
    1.68
     December
    1.63
     August
    1.63
    January
    1.59
     April
    1.59
     July
    1.55
     November
    1.55
     February
    1.51
    Activations Density 0.288%

    No Known Activations