© 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. 676
    Prev
    Next
    INDEX
    Explanations

    Ensure you of

    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
    ме
    0.27
    إ
    0.26
    ар
    0.26
    ራ
    0.26
    ан
    0.26
    γ
    0.26
    채
    0.25
    ум
    0.25
    ঙ্গল
    0.25
    onacci
    0.25
    POSITIVE LOGITS
    RELATIVA
    0.44
    <unused1089>
    0.43
     dont
    0.42
     consequently
    0.40
     sure
    0.40
     mich
    0.40
    
    0.40
     wasnt
    0.39
    <unused972>
    0.39
    之为
    0.39
    Activations Density 6.998%

    No Known Activations