© 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. 128114
    Prev
    Next
    INDEX
    Explanations

    lemish pály stāde يري éph dissati persiste stu Cura

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

    adverb-verb or verb-article

    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
    I
    0.65
    c
    0.58
    W
    0.58
    Step
    0.55
    С
    0.55
    CO
    0.54
    Think
    0.54
    cr
    0.53
    SP
    0.52
    S
    0.52
    POSITIVE LOGITS
    lemish
    0.47
     pály
    0.47
    }_{+}
    0.46
     stade
    0.45
    يري
    0.44
    éph
    0.44
     dissati
    0.44
     persiste
    0.43
     stu
    0.43
     Cura
    0.41
    Activations Density 0.002%

    No Known Activations