© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 193786
    Prev
    Next
    INDEX
    Explanations

    **Ctrl, Alt, Shift**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     Catholicism
    0.48
    യില്‍
    0.41
    実験
    0.38
    }))$
    0.38
    侾
    0.38
     রোহিঙ্গাদের
    0.38
    mination
    0.37
     függ
    0.36
    佰
    0.36
    メル
    0.35
    POSITIVE LOGITS
     diuretic
    0.42
     astring
    0.39
    하며
    0.39
    崚
    0.39
     miscon
    0.38
    垡
    0.38
     formulations
    0.37
    पश्च
    0.37
    äten
    0.37
    涩
    0.36
    Activations Density 0.000%

    No Known Activations