© 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. 136138
    Prev
    Next
    INDEX
    Explanations

    save or block data

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

    disruption and negative consequences

    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
     porté
    0.46
     dinding
    0.45
     উপেক্ষা
    0.45
     quitar
    0.44
     ў
    0.43
     קר
    0.43
     ג
    0.43
     geven
    0.43
     ፍ
    0.42
    Pane
    0.41
    POSITIVE LOGITS
     جماعت
    0.43
    ージ
    0.43
    μεσα
    0.42
     Handwriting
    0.41
     кораб
    0.40
     Hammond
    0.40
    isbury
    0.40
    偖
    0.39
     Ensures
    0.38
     Communications
    0.38
    Activations Density 0.000%

    No Known Activations