© 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. 136130
    Prev
    Next
    INDEX
    Explanations

    measurements and units

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

    essential for logic/operations

    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
    ״
    0.49
     շ
    0.46
    ופ
    0.44
     لن
    0.42
    won
    0.42
    দৃ
    0.42
     प्रश्
    0.41
    ים
    0.40
     Predictive
    0.40
    ⢿
    0.40
    POSITIVE LOGITS
     bigint
    0.44
    patan
    0.44
     evangel
    0.42
    LTE
    0.42
    ALING
    0.42
    免
    0.42
    MCC
    0.42
    LocalStorage
    0.41
     pesticide
    0.40
    बलेट
    0.40
    Activations Density 0.001%

    No Known Activations