© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 4805
    Prev
    Next
    INDEX
    Explanations

    code parameters and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     zak
    0.73
     bont
    0.67
    ）
    0.66
    While
    0.65
     While
    0.65
    ，$
    0.65
     good
    0.63
     Unfortunately
    0.62
     while
    0.62
     이번
    0.60
    POSITIVE LOGITS
    IDField
    0.86
    ネン
    0.85
    etrotters
    0.85
    észeti
    0.82
     terület
    0.82
     kohta
    0.81
    𓏧
    0.79
    瑁
    0.79
    了吗
    0.77
    𒊑
    0.77
    Activations Density 0.241%

    No Known Activations