© 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-262K
    7. 14316
    Prev
    Next
    INDEX
    Explanations

    logical consequence or deduction

    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_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
     complaints
    0.77
     complains
    0.75
     complain
    0.69
     xrange
    0.69
     oficialmente
    0.69
     मिमी
    0.69
     watchdog
    0.69
    ੲ
    0.67
    报警
    0.65
    尴
    0.65
    POSITIVE LOGITS
     follows
    1.49
    follows
    1.45
     Follow
    1.44
     follow
    1.43
    Follow
    1.38
     therefore
    1.36
    therefore
    1.33
    follow
    1.30
    Therefore
    1.30
     logically
    1.30
    Activations Density 0.086%

    No Known Activations