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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81182
    Prev
    Next
    INDEX
    Explanations

    scheduled another

    np_acts-logits-general · gemini-2.5-flash-lite

    definition and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    委员
    0.47
    好了
    0.46
    勍
    0.44
     elites
    0.44
     Fatima
    0.43
    领导
    0.43
    在这个
    0.42
    iora
    0.42
     Batista
    0.42
    抑
    0.42
    POSITIVE LOGITS
     הר
    0.52
    Track
    0.49
    ძლი
    0.49
     ഉപ
    0.49
     Prediction
    0.47
     klassischen
    0.46
    tdown
    0.46
    łego
    0.46
    Ě
    0.45
     offenen
    0.45
    Activations Density 0.000%

    No Known Activations