© 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. 115871
    Prev
    Next
    INDEX
    Explanations

    in followed by specific words

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

    negotiations or appraisals

    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
     разные
    0.47
     Телефон
    0.45
     различни
    0.44
     Wealth
    0.44
     песен
    0.43
     вол
    0.42
    вол
    0.41
    孰
    0.41
     жить
    0.40
     ужа
    0.40
    POSITIVE LOGITS
     providing
    0.50
    id
    0.47
    ificacion
    0.46
     دادن
    0.46
    يد
    0.45
    க்த
    0.45
     assisting
    0.44
    cja
    0.44
    ieving
    0.43
    providing
    0.43
    Activations Density 0.000%

    No Known Activations