© 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. 179385
    Prev
    Next
    INDEX
    Explanations

    fight for

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

    already, automatic, state

    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
     cytoplas
    0.44
     グリーン
    0.43
     catchy
    0.43
     respectable
    0.42
     söyledi
    0.42
     rebord
    0.42
    
    0.42
     Esq
    0.41
     ،
    0.41
     nylon
    0.41
    POSITIVE LOGITS
    正是
    0.52
    setTime
    0.45
    es
    0.44
    sha
    0.44
    yata
    0.44
    山
    0.43
    ião
    0.43
    지원
    0.43
    ONSE
    0.43
    ли
    0.42
    Activations Density 0.002%

    No Known Activations