© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11076
    Prev
    Next
    INDEX
    Explanations

    antipsychotic, AI alignment, explainability

    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
    на
    2.07
    est
    2.06
    en
    1.85
    st
    1.80
    ب
    1.77
    ש
    1.71
    רג
    1.70
    у
    1.62
    f
    1.62
    ್
    1.56
    POSITIVE LOGITS
    𝙤
    2.17
    𝙠
    2.16
    𝙜
    2.00
    𝙮
    1.98
    𝙞
    1.96
    𝙣
    1.94
    𝙛
    1.87
    𝙡
    1.86
    𝙊
    1.84
     onSubmit
    1.79
    Activations Density 0.008%

    No Known Activations