© 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. 231714
    Prev
    Next
    INDEX
    Explanations

    same style, own family, el camino

    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
    normalization
    0.52
    tourism
    0.46
    用於
    0.46
     რომელიც
    0.45
    followed
    0.44
    planting
    0.44
    table
    0.44
    ᄑ
    0.43
    toi
    0.42
    hitting
    0.42
    POSITIVE LOGITS
     sikap
    0.49
     nonprofit
    0.47
     selaku
    0.47
     acquaint
    0.45
     pesantren
    0.45
     harapan
    0.44
    źni
    0.44
     Denne
    0.44
    ье
    0.43
     Phúc
    0.43
    Activations Density 0.001%

    No Known Activations