© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 172543
    Prev
    Next
    INDEX
    Explanations

    of the

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

    auction audit

    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
     ਸ਼
    0.47
     namens
    0.45
    ٧
    0.45
     tinct
    0.45
     alkaloids
    0.44
     ebenfalls
    0.43
    鯽
    0.43
     Peruvian
    0.43
    reib
    0.42
    zte
    0.42
    POSITIVE LOGITS
    TimeStamp
    0.46
     posição
    0.44
    Ephemeral
    0.44
    ")
    0.42
    COOKIE
    0.42
    |".
    0.42
    VisualStudio
    0.42
    μό
    0.41
     时尚
    0.41
    single
    0.40
    Activations Density 0.001%

    No Known Activations