© 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. 218266
    Prev
    Next
    INDEX
    Explanations

    daily, with the, massage, malware encodes, the video, December the, accelerate the, continues to

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

    guidance and specifics

    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
     ны
    0.56
     वज
    0.54
    IAL
    0.52
    urned
    0.48
    ﺔ
    0.48
    IY
    0.48
     от
    0.48
    IE
    0.48
    たち
    0.48
    naie
    0.48
    POSITIVE LOGITS
     tumbling
    0.44
     tumble
    0.43
     MLS
    0.43
     Beweg
    0.42
     anyways
    0.41
     propiedades
    0.40
     denitrification
    0.40
    咩
    0.40
     Unite
    0.40
     Eigenschaften
    0.40
    Activations Density 0.000%

    No Known Activations