© 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. 125977
    Prev
    Next
    INDEX
    Explanations

    to be

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

    pricing and updates

    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
    ב
    0.55
    ו
    0.54
    顯示
    0.49
     connotations
    0.49
     kuid
    0.49
     echoed
    0.48
     buoyant
    0.48
     psychotic
    0.46
     nodal
    0.46
    ਰ
    0.46
    POSITIVE LOGITS
    ṟ
    0.47
     vitth
    0.46
     Benefits
    0.45
     Accounting
    0.44
    Ck
    0.44
     সঠিকভাবে
    0.44
    適切
    0.44
     Lot
    0.43
     Lush
    0.43
    COLOG
    0.43
    Activations Density 0.000%

    No Known Activations