© 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. 25198
    Prev
    Next
    INDEX
    Explanations

    urls or paths

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

    web navigation and code structure

    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
    django
    0.48
    Login
    0.48
    登
    0.46
     Login
    0.46
    登录
    0.43
    Django
    0.43
    公开
    0.42
    FormsModule
    0.42
     login
    0.42
    login
    0.42
    POSITIVE LOGITS
     cilind
    0.41
     refriger
    0.40
     aseg
    0.39
     pesar
    0.39
     tige
    0.39
    /√
    0.39
     frigor
    0.39
     cominc
    0.39
     extrapol
    0.39
     diamètre
    0.38
    Activations Density 0.000%

    No Known Activations