© 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. 109715
    Prev
    Next
    INDEX
    Explanations

    set/get methods

    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
    OrFail
    -0.77
    thisis
    -0.75
    cą
    -0.72
    DeepCopy
    -0.71
     Termin
    -0.71
    zheng
    -0.71
    utnik
    -0.71
    ﷲ
    -0.71
    raits
    -0.70
    avyzd
    -0.70
    POSITIVE LOGITS
     olup
    0.90
    illip
    0.80
     LATER
    0.79
    ilitation
    0.78
     septum
    0.75
    jutant
    0.74
     expliqué
    0.74
    brecht
    0.73
     açúcar
    0.72
     Novgorod
    0.72
    Activations Density 0.011%

    No Known Activations