© 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. 187694
    Prev
    Next
    INDEX
    Explanations

    packages, chains, done, Santa, iOS

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

    TNT YAML SAFE brine JSON

    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
    γχ
    0.47
    খ
    0.46
    فين
    0.46
    ियों
    0.45
    شته
    0.45
    )，
    0.45
    xSpeed
    0.45
    aría
    0.44
    <0x94>
    0.44
    ίναι
    0.44
    POSITIVE LOGITS
     Mih
    0.52
     Mitt
    0.52
    َّة
    0.52
     Republik
    0.51
     Boh
    0.50
     Nancy
    0.47
     Folk
    0.47
     Tornado
    0.46
     jut
    0.46
     Brus
    0.46
    Activations Density 0.000%

    No Known Activations