© 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. 156405
    Prev
    Next
    INDEX
    Explanations

    also

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

    specialised tests and new roles

    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
    عون
    0.50
    ロナ
    0.48
    باح
    0.46
    علی
    0.46
    ๓
    0.45
    كمال
    0.45
     ومع
    0.44
     artı
    0.44
    }})\
    0.44
    平凡
    0.42
    POSITIVE LOGITS
     have
    0.50
    άρ
    0.47
     neighbourhoods
    0.47
     curso
    0.46
     specialise
    0.46
     mone
    0.46
    have
    0.46
    তাহাকে
    0.45
     pohyb
    0.45
    城市
    0.45
    Activations Density 0.000%

    No Known Activations