© 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. 238880
    Prev
    Next
    INDEX
    Explanations

    . OSS from WiFi

    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
     filmm
    0.50
    ಾಗಿ
    0.48
     contador
    0.48
     nove
    0.46
    賈
    0.46
     checker
    0.45
     fac
    0.44
     afin
    0.43
     mote
    0.43
     ché
    0.43
    POSITIVE LOGITS
     устра
    0.48
    ua
    0.48
    uchos
    0.47
     מי
    0.45
    itos
    0.44
    aws
    0.44
    unsch
    0.43
    ußer
    0.43
    适用
    0.43
    ů
    0.43
    Activations Density 0.001%

    No Known Activations