© 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. 31665
    Prev
    Next
    INDEX
    Explanations

    mid market, RPG, pH, European

    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
    бина
    0.50
    ایک
    0.47
    élément
    0.46
    NumConst
    0.46
    
    0.46
    TRY
    0.45
    鐢
    0.44
    Най
    0.43
    Grun
    0.43
    ROR
    0.43
    POSITIVE LOGITS
     Unesco
    0.46
     Legislative
    0.44
     it
    0.43
     http
    0.43
    0.42
     It
    0.42
     NGOs
    0.42
     WTO
    0.41
     Parlament
    0.41
     downtown
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.