© 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. 35650
    Prev
    Next
    INDEX
    Explanations

    quantifiers and specific items

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

    descriptive word followed by noun

    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
    。
    0.42
    ।
    0.39
     этом
    0.36
    というと
    0.30
    に対し
    0.29
     पार्श्व
    0.29
    더
    0.29
    》，
    0.29
     उसे
    0.29
     들
    0.29
    POSITIVE LOGITS
    -
    0.46
    volle
    0.36
    ”、“
    0.33
    မဲ့
    0.32
    7
    0.32
    yuan
    0.31
    <unused278>
    0.31
    」「
    0.30
    <unused1991>
    0.30
    ratulations
    0.30
    Activations Density 0.058%

    No Known Activations