© 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. 182429
    Prev
    Next
    INDEX
    Explanations

    favourite dog

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

    giving support to groups or individuals

    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
    放心
    0.52
    प्ताह
    0.47
     သူ
    0.47
    ㅎ
    0.47
    failed
    0.46
    печа
    0.46
    tough
    0.46
    谢
    0.46
    inol
    0.45
    れ
    0.45
    POSITIVE LOGITS
     metap
    0.56
     Equ
    0.54
     Gens
    0.51
     sedent
    0.50
     SID
    0.50
     ARI
    0.48
     CUR
    0.48
     Data
    0.47
     Brussels
    0.46
     mask
    0.46
    Activations Density 0.000%

    No Known Activations