© 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. 47885
    Prev
    Next
    INDEX
    Explanations

    contractual or for

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

    code symbols and programming concepts

    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
     verrez
    0.51
     couverts
    0.50
    酗
    0.48
    会の
    0.46
    รวจ
    0.46
    清潔
    0.45
     অপরিচিত
    0.44
    车辆
    0.43
    ㊗
    0.43
     території
    0.43
    POSITIVE LOGITS
     escrit
    0.44
    ný
    0.42
    ها
    0.41
     ره
    0.40
     pur
    0.40
     Guang
    0.39
     side
    0.38
     కల
    0.38
     flanking
    0.38
    pay
    0.38
    Activations Density 0.000%

    No Known Activations