© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177462
    Prev
    Next
    INDEX
    Explanations

    ratings and units

    np_acts-logits-general · gemini-2.5-flash-lite

    misconduct, Thin, Bard, breath, layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     உள
    0.43
    LAYOUT
    0.42
    旖
    0.41
     पवित्र
    0.41
    ന്യാ
    0.41
    ंसक
    0.40
    ma
    0.39
    യ
    0.39
    颀
    0.39
    alá
    0.39
    POSITIVE LOGITS
     કરાવ
    0.43
     شهد
    0.42
    ังกฤษ
    0.42
     outperformed
    0.42
     smelled
    0.42
     revolved
    0.42
    ்டோ
    0.42
     subscribed
    0.42
     dehyd
    0.41
     tasted
    0.41
    Activations Density 0.002%

    No Known Activations