© 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. 11038
    Prev
    Next
    INDEX
    Explanations

    Thank you

    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
    ς
    4.15
    ً
    3.55
    s
    3.44
    ات
    3.10
     desse
    2.96
    য়ের
    2.90
    য়ের
    2.87
    ากหลาย
    2.86
    ਆਂ
    2.81
    т
    2.67
    POSITIVE LOGITS
    م
    3.74
    er
    3.22
    staking
    3.12
    ers
    3.04
    ுள்ள
    2.99
    ህ
    2.94
    ी
    2.90
    あげ
    2.88
    িস
    2.83
    何を
    2.82
    Activations Density 0.006%

    No Known Activations