© 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. 31-GEMMASCOPE-2-RES-262K
    7. 23646
    Prev
    Next
    INDEX
    Explanations

    grammatical gender and loans

    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_31_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
     hemicontinuous
    0.49
    韩
    0.48
     韩
    0.47
    醝
    0.44
    ⵎ
    0.44
     网络
    0.42
    𝟐
    0.41
    xcodep
    0.41
     باي
    0.41
    맇
    0.41
    POSITIVE LOGITS
     and
    0.53
    family
    0.47
    judgment
    0.44
    oubt
    0.43
    application
    0.43
    foreground
    0.42
     và
    0.41
    driven
    0.41
     μας
    0.40
     admiration
    0.40
    Activations Density 0.003%

    No Known Activations