© 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. 224246
    Prev
    Next
    INDEX
    Explanations

    introduction to capabilities

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

    time frames and durations

    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
     সকলেই
    0.46
     ataupun
    0.45
     innerhalb
    0.43
     kelamin
    0.43
    ()[
    0.43
    ә
    0.43
     beispielsweise
    0.42
     poseen
    0.42
     тип
    0.42
    си
    0.41
    POSITIVE LOGITS
     Groom
    0.47
    \
    0.46
    다
    0.45
    정을
    0.45
    time
    0.44
     ถ้า
    0.44
     좋은
    0.43
     얻
    0.43
     ನಮ್ಮ
    0.43
    ד
    0.42
    Activations Density 0.001%

    No Known Activations