© 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. 37273
    Prev
    Next
    INDEX
    Explanations

    doing a, km (, stays,

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

    multilingual nature descriptions

    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
     Dou
    0.43
     Tower
    0.41
     Duo
    0.39
     Extra
    0.39
     °
    0.38
     CLA
    0.37
     NPM
    0.37
     تقریبا
    0.37
     Exter
    0.37
    ˚
    0.37
    POSITIVE LOGITS
    リル
    0.42
    セス
    0.42
     stripos
    0.42
     giocare
    0.42
     اليمن
    0.42
     அவள்
    0.42
    हायला
    0.41
    PlatformTarget
    0.41
     Sarasota
    0.41
    あなたが
    0.41
    Activations Density 0.000%

    No Known Activations