© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12284
    Prev
    Next
    INDEX
    Explanations

    correlation between

    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
    Negative Logits
    ем
    3.29
    د
    2.99
    Время
    2.96
    éral
    2.92
    al
    2.89
    ement
    2.62
    ekt
    2.59
    elijke
    2.57
    hombre
    2.51
    hora
    2.49
    POSITIVE LOGITS
    𝙇
    3.54
    𝙢
    3.07
    行う
    2.94
    codile
    2.91
    𝙉
    2.87
     IRAS
    2.84
    𝘿
    2.81
    𝙩
    2.80
    𝙊
    2.78
     reigning
    2.76
    Activations Density 0.042%

    No Known Activations