© 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. 31104
    Prev
    Next
    INDEX
    Explanations

    transactions and entities

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

    understanding new concepts

    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
     остальных
    0.49
    ar
    0.47
    偵
    0.47
     Adriatic
    0.47
     OUTER
    0.47
     CLIENT
    0.46
    in
    0.46
    갤럭
    0.45
     IOException
    0.45
    ，
    0.45
    POSITIVE LOGITS
    qualität
    0.47
    DeathRecord
    0.46
    Noir
    0.43
    Ans
    0.42
    ‪
    0.41
    牵
    0.40
    Centro
    0.40
    JobID
    0.40
    Gear
    0.40
     כמה
    0.40
    Activations Density 0.000%

    No Known Activations