© 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. 182417
    Prev
    Next
    INDEX
    Explanations

    describing length, uniqueness, complexity, or type

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

    lack of something

    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
    豆
    0.49
     kuten
    0.47
     práci
    0.47
     neki
    0.43
    ナー
    0.43
    BEAN
    0.43
    бе
    0.42
    ρε
    0.42
     Peers
    0.42
    ミ
    0.41
    POSITIVE LOGITS
    ructured
    0.47
    amentales
    0.44
     encontramos
    0.44
     psychologically
    0.44
    quired
    0.44
    heartedly
    0.44
    ForegroundColor
    0.43
     Alonso
    0.43
     frequented
    0.43
     aclarar
    0.43
    Activations Density 0.001%

    No Known Activations