© 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. 159617
    Prev
    Next
    INDEX
    Explanations

    you may not assign

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

    consistency, involved, share

    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
    一点
    0.50
     Wellbeing
    0.44
    刘
    0.44
     Brus
    0.43
     Prosecutor
    0.42
     Runner
    0.42
     Agencies
    0.42
     Passenger
    0.41
     Diner
    0.40
     Walth
    0.40
    POSITIVE LOGITS
    equ
    0.52
    emor
    0.50
     فلس
    0.49
    ebo
    0.47
    тивний
    0.47
    stva
    0.47
    𝐞
    0.46
     жизнь
    0.46
    ць
    0.46
     рі
    0.46
    Activations Density 0.001%

    No Known Activations