© 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. 210110
    Prev
    Next
    INDEX
    Explanations

    official conditions, market status

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

    personal identifiable information

    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
     obiekt
    0.52
    يس
    0.46
     ظ
    0.46
     ausführ
    0.45
    ხედ
    0.44
    كرة
    0.44
    屆
    0.44
    رح
    0.43
     zicht
    0.43
    కోవడం
    0.43
    POSITIVE LOGITS
     PR
    0.53
     graines
    0.46
     ভাঙ
    0.46
     EDGE
    0.46
     necesitar
    0.45
     acidified
    0.45
     spoonful
    0.44
    の場合
    0.44
     βοη
    0.44
     PAR
    0.43
    Activations Density 0.002%

    No Known Activations