© 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. 13884
    Prev
    Next
    INDEX
    Explanations

    youtube links, http, phone numbers

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

    conversational variations

    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
    。”
    0.41
    ។
    0.38
    。
    0.38
    ，
    0.37
    .}
    0.36
    .`
    0.35
     쉽게
    0.35
    .??
    0.35
     하나의
    0.35
     oa
    0.34
    POSITIVE LOGITS
     পিঁপড়া
    0.35
     বাহাদুর
    0.35
    ahkan
    0.34
    ły
    0.33
    ly
    0.32
    စ
    0.32
    lym
    0.32
    kaa
    0.32
    缦
    0.32
    umba
    0.31
    Activations Density 0.011%

    No Known Activations