© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8508
    Prev
    Next
    INDEX
    Explanations

    SAMHSA helpline H

    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_9_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
    a
    1.66
    y
    1.60
    る
    1.51
    ت
    1.48
    ের
    1.45
    া
    1.45
    ing
    1.44
    ০
    1.40
    is
    1.35
    aan
    1.33
    POSITIVE LOGITS
    бліоте
    1.07
     nesse
    1.05
    imageNamed
    1.05
    llllll
    1.01
    是在
    1.00
    Là
    0.98
     नवंबर
    0.97
    ﾗ
    0.97
    臾
    0.96
     ske
    0.96
    Activations Density 0.047%

    No Known Activations