© 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. 41-GEMMASCOPE-2-RES-262K
    7. 7876
    Prev
    Next
    INDEX
    Explanations

    scalar values

    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_all/layer_41_width_262k_l0_big
    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
    ティーク
    0.43
     работо
    0.42
    姏
    0.41
     ऑर्गेनिक
    0.41
    ເຄ
    0.41
    touchstart
    0.40
    dateFormat
    0.39
    㓶
    0.39
    വിധ
    0.39
     professionnelle
    0.39
    POSITIVE LOGITS
     scalar
    3.14
     Scalar
    2.92
    scalar
    2.84
    Scalar
    2.80
     scalars
    2.77
    scalars
    2.25
     Scalars
    2.22
    Scalars
    2.05
     escalar
    1.86
     scaler
    1.52
    Activations Density 0.007%

    No Known Activations