© 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. 9379
    Prev
    Next
    INDEX
    Explanations

    did the dishes

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

    guy walks into a shop asking

    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
    ลีก
    0.45
    ंकिंग
    0.44
    棤
    0.44
     použív
    0.44
    }$\
    0.43
    vendo
    0.42
    kill
    0.42
    𓈒
    0.42
    olved
    0.41
    Nak
    0.41
    POSITIVE LOGITS
     normalcy
    0.46
     opined
    0.46
     fractures
    0.43
     impedances
    0.42
     tensions
    0.42
     Imped
    0.42
     strategically
    0.42
    ಷ
    0.42
     squaring
    0.41
     ৬৬
    0.41
    Activations Density 0.000%

    No Known Activations