© 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. 87616
    Prev
    Next
    INDEX
    Explanations

    week later

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

    anime, bonus, hacking, animal models

    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
    u
    0.56
     Program
    0.52
    Program
    0.52
    تیب
    0.52
    I
    0.52
    bold
    0.48
    Ta
    0.47
    وین
    0.47
    Parent
    0.46
     Write
    0.46
    POSITIVE LOGITS
     обеспечение
    0.49
     ૩
    0.48
    ésus
    0.47
    netHex
    0.47
     বাড়িতে
    0.45
    ệc
    0.45
    straße
    0.45
     стандарта
    0.45
     مزاج
    0.45
     ජ
    0.45
    Activations Density 0.001%

    No Known Activations