© 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. 235942
    Prev
    Next
    INDEX
    Explanations

    members-only, results, barcodes

    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
    s
    0.49
    这样一个
    0.48
     chaotic
    0.46
     destructive
    0.44
    Ending
    0.43
     الرغم
    0.42
    壊
    0.42
     않는
    0.42
     trotz
    0.42
     خوف
    0.42
    POSITIVE LOGITS
    ॉक
    0.57
    पुढे
    0.51
    귤
    0.51
     photographers
    0.50
     인증
    0.49
     hikers
    0.49
     코드
    0.48
     pork
    0.48
     barcodes
    0.48
    जेक्ट
    0.47
    Activations Density 0.002%

    No Known Activations