© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132167
    Prev
    Next
    INDEX
    Explanations

    word followed by noun or verb

    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
    𝙨
    0.43
    行动
    0.41
     синте
    0.41
     Благо
    0.41
     달
    0.40
     STUDIES
    0.39
    ispiel
    0.39
     अनलि
    0.38
    人了
    0.38
    Preset
    0.38
    POSITIVE LOGITS
     wording
    0.44
     લ
    0.43
     worded
    0.40
     lid
    0.39
     respective
    0.39
     lids
    0.39
    ರುತ್ತವೆ
    0.39
     olev
    0.39
     burned
    0.38
     wyd
    0.38
    Activations Density 0.004%

    No Known Activations