© 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. 249497
    Prev
    Next
    INDEX
    Explanations

    take a

    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
    சை
    0.43
     нико
    0.42
    ATHER
    0.42
    indak
    0.40
    數
    0.40
     metallic
    0.40
     எச்ச
    0.40
    ép
    0.40
     가지
    0.40
     never
    0.39
    POSITIVE LOGITS
    ႏ
    0.49
    PrivateRoute
    0.46
     Mikel
    0.45
     Cpu
    0.45
     Screenshots
    0.45
     Anakin
    0.45
    স্তাফিজ
    0.45
     Smoothing
    0.44
    也就是说
    0.43
     Imran
    0.43
    Activations Density 0.001%

    No Known Activations