© 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. 24579
    Prev
    Next
    INDEX
    Explanations

    code definition and block start

    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
    Prefix
    0.43
    迭
    0.41
    既然
    0.40
     occupied
    0.40
     করাতে
    0.39
    าก
    0.39
    าท
    0.39
    麹
    0.39
    าม
    0.39
     pairwise
    0.39
    POSITIVE LOGITS
     Kald
    0.52
    ჯ
    0.52
    жы
    0.51
    até
    0.50
     étudiants
    0.48
     விழுப்புரம்
    0.47
     tý
    0.47
    胄
    0.46
    rza
    0.46
    mobilpay
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.