© 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. 168987
    Prev
    Next
    INDEX
    Explanations

    collocations and grammatical continuations

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

    language, translation, sequence

    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
    f
    0.49
    niew
    0.49
    newBuilder
    0.48
    qu
    0.48
    jelen
    0.47
    ar
    0.47
    crate
    0.47
    enc
    0.46
    dv
    0.46
    ch
    0.46
    POSITIVE LOGITS
    陖
    0.49
     Đảng
    0.46
     감
    0.46
    Vg
    0.46
     aldehyde
    0.44
     暗
    0.43
     gneiss
    0.43
    }}+\
    0.42
     여기가
    0.42
    喑
    0.42
    Activations Density 0.000%

    No Known Activations