© 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. 110483
    Prev
    Next
    INDEX
    Explanations

    set foot on

    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
    vodu
    -0.93
     andrea
    -0.79
    空格
    -0.78
    ↣
    -0.77
    ilíbrio
    -0.76
     toledo
    -0.76
    classnames
    -0.75
    Ⅺ
    -0.74
    straight
    -0.74
    ISTRY
    -0.73
    POSITIVE LOGITS
     foot
    2.50
     set
    2.48
     step
    2.38
     stepping
    2.09
     stepped
    2.06
    step
    1.80
     setting
    1.77
    stepping
    1.75
    Step
    1.74
    踏
    1.74
    Activations Density 0.029%

    No Known Activations