© 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. 26601
    Prev
    Next
    INDEX
    Explanations

    Yoga University or simple theme

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

    non-english words

    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
     metamorph
    0.45
     milliamperes
    0.42
     or
    0.42
     headquarters
    0.42
     metamorphosis
    0.42
     reac
    0.41
     ή
    0.41
     alebo
    0.41
     أو
    0.40
    たる
    0.40
    POSITIVE LOGITS
    栊
    0.50
    goài
    0.46
    రికీ
    0.46
    买
    0.45
    무
    0.44
    ा
    0.43
    뒀
    0.42
    未来
    0.42
     ентите
    0.42
    ाना
    0.41
    Activations Density 0.000%

    No Known Activations