© 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. 198465
    Prev
    Next
    INDEX
    Explanations

    promise warranty

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

    writing, translating, recommending, crafting

    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
     mất
    0.48
    গত
    0.47
     favicon
    0.45
     and
    0.44
    ρα
    0.43
     ベ
    0.42
     =====
    0.42
     selfie
    0.41
     wakt
    0.41
     теря
    0.41
    POSITIVE LOGITS
    ishna
    0.48
     youngsters
    0.45
    insch
    0.45
    ]^{\
    0.44
    kowe
    0.44
     نوش
    0.43
    }}{
    0.42
    nok
    0.42
    wold
    0.42
    HandleFunc
    0.42
    Activations Density 0.000%

    No Known Activations