© 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. 30931
    Prev
    Next
    INDEX
    Explanations

    choose the right

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

    sharp angles

    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
     ಉತ್
    0.52
    𝟎
    0.52
    Depart
    0.50
     почти
    0.50
     finalList
    0.49
    Casc
    0.47
    LIST
    0.46
     थोरो
    0.46
     записы
    0.46
     ஒன்று
    0.45
    POSITIVE LOGITS
     soothing
    0.42
    мих
    0.42
    煂
    0.40
     expedite
    0.40
    薯
    0.39
    ester
    0.39
    كنولوجيا
    0.39
    รวจ
    0.39
     vita
    0.38
     pebble
    0.38
    Activations Density 0.000%

    No Known Activations