© 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. 202431
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs and completions

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

    describing requirements or quality

    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
     asserted
    0.61
     Дже
    0.51
     numerosos
    0.49
     fhe
    0.48
     ﺍ
    0.48
     registros
    0.47
     afferma
    0.47
     деву
    0.46
     affirmed
    0.46
     tabled
    0.46
    POSITIVE LOGITS
     Tuk
    0.54
    ylus
    0.53
    baka
    0.49
    ôn
    0.47
    醅
    0.47
    Painting
    0.47
    Rot
    0.46
    Butyl
    0.46
     populations
    0.46
    yles
    0.45
    Activations Density 0.000%

    No Known Activations