© 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. 134705
    Prev
    Next
    INDEX
    Explanations

    anonymous tip

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

    a powerful reinforcement learning algorithm

    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
    SCO
    0.55
    LL
    0.52
     多く
    0.52
    FromString
    0.50
     స
    0.50
     ولي
    0.48
     ابي
    0.48
    га
    0.47
     সাদ
    0.47
    FAKE
    0.47
    POSITIVE LOGITS
     Ad
    0.53
     Eighty
    0.47
    🕘
    0.44
     sintomas
    0.43
    imas
    0.43
     Patna
    0.43
     Sixty
    0.43
     Padua
    0.42
     Alexandra
    0.42
    ریق
    0.41
    Activations Density 0.000%

    No Known Activations