© 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. 9254
    Prev
    Next
    INDEX
    Explanations

    condition analysis cells

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

    file paths and code snippets

    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
     vielfält
    0.40
    โป
    0.40
    ⨔
    0.39
     अचार
    0.38
    ัพท์
    0.38
    嬗
    0.38
    pOt
    0.38
    ᐛ
    0.38
     व्यंजनों
    0.37
     druhé
    0.37
    POSITIVE LOGITS
     belong
    0.37
     administered
    0.35
     globally
    0.35
     რომელიც
    0.35
     yine
    0.34
     emanating
    0.34
     timestamp
    0.34
     always
    0.33
    出自
    0.33
     koje
    0.32
    Activations Density 0.007%

    No Known Activations