© 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. 259134
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     продолжаем
    0.45
    睑
    0.43
    मल
    0.42
    总结
    0.42
    Telefono
    0.41
    ☦
    0.40
    听到
    0.40
    季
    0.40
    毗
    0.40
     시작하겠습니다
    0.40
    POSITIVE LOGITS
     Rohing
    0.51
     yard
    0.46
     rogue
    0.46
     Lieut
    0.45
     anarchist
    0.45
     futuristic
    0.44
     Vote
    0.44
     Deadpool
    0.44
     Spectre
    0.44
     Llan
    0.44
    Activations Density 0.001%

    No Known Activations