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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138778
    Prev
    Next
    INDEX
    Explanations

    understand subject matter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !
    0.57
    lier
    0.53
    ?
    0.53
    saldo
    0.47
    !</
    0.46
     fio
    0.46
     pror
    0.45
    lage
    0.44
    stro
    0.44
    ticket
    0.43
    POSITIVE LOGITS
     Principles
    0.55
    िकल्स
    0.54
     européens
    0.51
     ۹
    0.49
    Principles
    0.49
    мов
    0.47
    ේශ
    0.47
     Europese
    0.46
     étrangères
    0.46
    icycles
    0.46
    Activations Density 0.000%

    No Known Activations