© 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. 170031
    Prev
    Next
    INDEX
    Explanations

    vote or registering

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

    fund strategies, regrets about, brush strokes, petals speckled

    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
    சல்
    0.46
     delay
    0.46
     tumhe
    0.45
    千年
    0.44
    なかなか
    0.43
    хие
    0.43
    ********/
    0.43
     trope
    0.42
    妷
    0.42
    დილ
    0.41
    POSITIVE LOGITS
     הא
    0.47
     використо
    0.47
     الطفل
    0.47
     Campeonato
    0.46
     হ্যান্ড
    0.45
     fär
    0.44
     Prepar
    0.43
     Preferably
    0.43
    LO
    0.43
     أيضا
    0.43
    Activations Density 0.000%

    No Known Activations