© 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. 218758
    Prev
    Next
    INDEX
    Explanations

    shooting disciplines

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

    verify a fisherman's claims

    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
    ḷ
    0.52
     கே
    0.50
     ধর্ষণ
    0.49
    featuring
    0.49
     ჟ
    0.46
     टीच
    0.46
     রয়েছে
    0.46
     도와
    0.46
    🖼
    0.46
    immagine
    0.46
    POSITIVE LOGITS
     affidavits
    0.48
     remedial
    0.47
     salvage
    0.46
     Affidavit
    0.46
     vacation
    0.46
     consultants
    0.45
     transatlantic
    0.44
     transplant
    0.42
     perishable
    0.42
     but
    0.41
    Activations Density 0.001%

    No Known Activations