© 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. 155582
    Prev
    Next
    INDEX
    Explanations

    locations and relationships

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

    bricks, values, stories

    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
    ле
    0.50
    xing
    0.46
    x
    0.46
     kautta
    0.44
    ез
    0.43
    jarige
    0.43
    eg
    0.43
    ്ര
    0.43
    et
    0.42
     NSFW
    0.42
    POSITIVE LOGITS
    یده
    0.44
     suppos
    0.43
    щают
    0.42
     멋
    0.42
    msgSender
    0.41
    牀
    0.41
    明確
    0.40
    囁
    0.40
     योजनाओं
    0.40
    क्तिक
    0.40
    Activations Density 0.001%

    No Known Activations