© 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. 136817
    Prev
    Next
    INDEX
    Explanations

    obligation to update

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

    commands, talking, charger, creation

    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
    М
    0.48
    ettore
    0.48
    𝐺
    0.47
    Цент
    0.47
    überküloz
    0.46
    捪
    0.45
     яка
    0.44
    𝗦
    0.44
     Стро
    0.43
    ರವ
    0.43
    POSITIVE LOGITS
     নষ্ট
    0.47
     n
    0.46
     创建
    0.44
    adería
    0.43
     decommission
    0.42
     लॉ
    0.42
     memang
    0.42
     ochr
    0.41
     townhouse
    0.41
     vám
    0.41
    Activations Density 0.000%

    No Known Activations