© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1014
    Prev
    Next
    INDEX
    Explanations

    description of a person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    fehlung
    0.92
    ıkl
    0.90
     hulle
    0.84
    itul
    0.81
     prehr
    0.75
    beschreibung
    0.74
    ydın
    0.73
    滂
    0.72
    ataan
    0.71
    좔
    0.71
    POSITIVE LOGITS
     crimes
    1.77
    beds
    1.72
    okie
    1.68
    kingdom
    1.67
    rones
    1.67
     regimes
    1.64
    opharmaceuticals
    1.63
    bearing
    1.62
    eliers
    1.62
    cinas
    1.62
    Activations Density 0.291%

    No Known Activations