© 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. 124626
    Prev
    Next
    INDEX
    Explanations

    private positions

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

    direction, change, or condition

    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
    밂
    0.46
    ローチ
    0.45
    觓
    0.45
     sexe
    0.44
     cashier
    0.44
     naam
    0.42
     カラ
    0.42
    })$;
    0.42
     proveedor
    0.42
    olet
    0.42
    POSITIVE LOGITS
     CDs
    0.48
    To
    0.43
    izing
    0.42
    问道
    0.42
    izza
    0.41
     जानकारियां
    0.40
    ValueChanged
    0.40
     Citizens
    0.39
    Cities
    0.39
     khiến
    0.39
    Activations Density 0.001%

    No Known Activations