© 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. 208923
    Prev
    Next
    INDEX
    Explanations

    * or ™ followed by players

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

    defining code parameters and configurations

    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
     안에
    0.47
    INTER
    0.47
     όπου
    0.46
    MOD
    0.46
     Якщо
    0.46
    TEXT
    0.45
    ತೆಗೆ
    0.45
    |_
    0.45
    USER
    0.44
    LIST
    0.44
    POSITIVE LOGITS
     disgraceful
    0.44
     комиссии
    0.44
     consens
    0.42
     academically
    0.42
     strana
    0.42
     shameful
    0.41
     strained
    0.40
     Kimberly
    0.40
    ي
    0.40
     pár
    0.40
    Activations Density 0.000%

    No Known Activations