© 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-65K
    7. 1358
    Prev
    Next
    INDEX
    Explanations

    imagine you

    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_65k_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
    vient
    0.49
    DeathRecord
    0.47
     பார்க்கும்
    0.46
    🆙
    0.46
    <unused58>
    0.46
    chyné
    0.46
    BleStatus
    0.45
     እንቅ
    0.45
    anggilan
    0.45
     মিনিট
    0.44
    POSITIVE LOGITS
    1
    0.64
     damaging
    0.61
    2
    0.61
     a
    0.52
     needed
    0.51
    0
    0.51
     carry
    0.49
    ade
    0.48
    G
    0.47
     Other
    0.47
    Activations Density 0.003%

    No Known Activations