© 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. 44086
    Prev
    Next
    INDEX
    Explanations

    information and assessment

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

    testing and "Ribbit?"

    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
    реа
    0.48
    ಹ
    0.48
    ة
    0.48
    吳
    0.48
    ρά
    0.45
    ㄢ
    0.44
    امج
    0.44
    ో
    0.43
     convenient
    0.43
    хра
    0.43
    POSITIVE LOGITS
    chrift
    0.52
     bertahan
    0.52
     atenção
    0.45
     ہون
    0.45
    ável
    0.44
     dour
    0.44
    ían
    0.44
     atención
    0.44
     pide
    0.42
     devait
    0.42
    Activations Density 0.000%

    No Known Activations