© 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. 6984
    Prev
    Next
    INDEX
    Explanations

    as followed by descriptive phrase

    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
    ن
    1.26
    ت
    1.25
    ний
    1.20
    تر
    1.08
    一个是
    0.93
    ния
    0.89
    et
    0.87
    تن
    0.84
    นี่
    0.84
    ה
    0.84
    POSITIVE LOGITS
     opposed
    2.02
    ymmet
    1.92
     follows
    1.83
    cribing
    1.71
    sembles
    1.67
     evidenced
    1.67
     well
    1.59
     soon
    1.56
    cribes
    1.55
    cribable
    1.52
    Activations Density 0.162%

    No Known Activations