© 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. 10907
    Prev
    Next
    INDEX
    Explanations

    face / faces / faced

    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
    ি
    3.35
    ु
    3.16
    ی
    3.04
    te
    2.98
    𝗔
    2.85
    ]}(
    2.85
    ні
    2.82
    ி
    2.82
    𝗢
    2.75
    steak
    2.69
    POSITIVE LOGITS
     trận
    3.47
    颊
    2.98
    egen
    2.96
     monde
    2.95
     собой
    2.95
    ان
    2.79
     attenzione
    2.72
    ering
    2.71
     собою
    2.68
    意思是
    2.65
    Activations Density 0.056%

    No Known Activations