© 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. 59774
    Prev
    Next
    INDEX
    Explanations

    date, time, count

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

    still followed by location or 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
     tuf
    0.46
    க்கொண்டு
    0.44
    ダウン
    0.43
     製
    0.43
     schönsten
    0.43
    vedo
    0.43
    に取り組
    0.43
     производства
    0.43
     contar
    0.42
    epoca
    0.42
    POSITIVE LOGITS
    ConnectionType
    0.42
     homelessness
    0.42
    \%.
    0.40
    Socket
    0.40
     Allocation
    0.40
     heartbreak
    0.40
    开头
    0.39
    *.
    0.38
    setName
    0.38
    Question
    0.38
    Activations Density 0.000%

    No Known Activations