© 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. 223443
    Prev
    Next
    INDEX
    Explanations

    derived ingredients

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

    What about or more like

    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
    浄
    0.50
    Investor
    0.50
    지는
    0.49
    ಿಸ
    0.48
    }}}$
    0.47
    지로
    0.47
    贮
    0.47
    貯
    0.46
    ices
    0.45
    지
    0.45
    POSITIVE LOGITS
     viszont
    0.52
     entrando
    0.49
     কালিক
    0.48
     الطريق
    0.46
    فر
    0.46
     mirrored
    0.46
     তেমনই
    0.46
     Hayley
    0.46
     vielen
    0.45
     தாக்க
    0.45
    Activations Density 0.000%

    No Known Activations