© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15552
    Prev
    Next
    INDEX
    Explanations

    words after "if" or "is"

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

    common word followed by descriptive word

    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_16k_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
     Reihen
    0.51
     fidèle
    0.51
    ERSON
    0.51
     =,
    0.51
     கூறப்படுகிறது
    0.51
    怎
    0.48
    里昂
    0.47
    Dalam
    0.47
    Waar
    0.47
    Ibid
    0.46
    POSITIVE LOGITS
    oretically
    0.93
     and
    0.70
    .
    0.69
    نے
    0.68
    8
    0.65
     as
    0.64
    ской
    0.62
    ق
    0.60
     or
    0.59
    ية
    0.56
    Activations Density 0.747%

    No Known Activations