© 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. 40052
    Prev
    Next
    INDEX
    Explanations

    actual results and variations

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

    actual outcomes and details

    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
     җиңү
    0.42
    计量
    0.40
    spider
    0.38
     Allow
    0.37
    كه
    0.37
     Allows
    0.36
    앵
    0.36
     ያሉ
    0.36
    檢
    0.36
     botanical
    0.36
    POSITIVE LOGITS
     devido
    0.53
     déterminé
    0.49
     dispuestos
    0.46
    Incidentally
    0.46
     tâches
    0.45
     aufgrund
    0.45
     due
    0.44
     بسبب
    0.44
     vítimas
    0.44
     debido
    0.44
    Activations Density 0.002%

    No Known Activations