© 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. 37632
    Prev
    Next
    INDEX
    Explanations

    confidence interval or interquartile range

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

    murderer, score, medium

    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
    ^{\
    0.46
    NB
    0.46
    ")
    0.45
    "_
    0.45
    (*
    0.44
    ”)
    0.44
    ",
    0.43
    *>
    0.43
    “)
    0.43
    findAll
    0.43
    POSITIVE LOGITS
     คะแนน
    0.46
     Riders
    0.45
     gigante
    0.44
     ranking
    0.43
     USPS
    0.43
     स्कोर
    0.42
     Rider
    0.42
    大赛
    0.42
     Drapeau
    0.42
     Rank
    0.42
    Activations Density 0.000%

    No Known Activations