© 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. 175604
    Prev
    Next
    INDEX
    Explanations

    produced a, final circuit, magical process

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

    volatility remains, rhythmic clang

    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
     jLabel
    0.46
    ButtonItem
    0.46
    痰
    0.44
    quet
    0.44
    ătur
    0.44
    adamente
    0.43
     Fitzgerald
    0.43
    ít
    0.42
    ্সি
    0.42
     động
    0.42
    POSITIVE LOGITS
    கோ
    0.56
    い
    0.53
     signify
    0.51
    އ
    0.48
    Ка
    0.48
     모습
    0.47
    Σ
    0.47
    މ
    0.46
     оказались
    0.46
    カ
    0.46
    Activations Density 0.000%

    No Known Activations