© 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. 133930
    Prev
    Next
    INDEX
    Explanations

    actions or states following specific words

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

    from __future__ import annotations

    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
     क्वेश्चंस
    0.52
     дуже
    0.49
    溆
    0.49
    ش
    0.46
    Alic
    0.45
     Ergebn
    0.44
     appunto
    0.44
     Rows
    0.44
    场
    0.43
    스러
    0.43
    POSITIVE LOGITS
    imt
    0.49
     grows
    0.48
     fastapi
    0.46
        
    0.46
     breed
    0.45
     mult
    0.45
     hotel
    0.44
    astar
    0.44
       
    0.43
     _
    0.43
    Activations Density 0.001%

    No Known Activations