© 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. 125096
    Prev
    Next
    INDEX
    Explanations

    favorite place, Korea, follow, favorite bird, automatically, grandmother

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

    Ephesians keto Flatten

    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
    ográficos
    0.51
    積極的に
    0.48
    Secondo
    0.47
    で
    0.47
     ejecut
    0.47
    André
    0.46
    ných
    0.46
    Hector
    0.45
    पिछले
    0.45
     अन्यथा
    0.45
    POSITIVE LOGITS
    SError
    0.46
    باد
    0.46
    State
    0.43
    Status
    0.42
    alne
    0.41
    "*
    0.40
    limits
    0.40
    uola
    0.40
    arynx
    0.40
     kolejne
    0.40
    Activations Density 0.000%

    No Known Activations