© 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. 118972
    Prev
    Next
    INDEX
    Explanations

    Java code syntax

    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
    izzati
    -1.11
    Източници
    -1.03
    ّه
    -0.92
    mung
    -0.89
    wab
    -0.88
    Gdzie
    -0.84
     ग्राहकों
    -0.84
     зелены
    -0.81
    izop
    -0.81
     半袖
    -0.81
    POSITIVE LOGITS
    ;->
    1.14
    EDEFAULT
    1.01
    $$
    0.94
    ((
    0.92
    Ljava
    0.91
    Anonymous
    0.91
     oignons
    0.90
     todavía
    0.90
     jeszcze
    0.89
    breviations
    0.88
    Activations Density 0.004%

    No Known Activations