© 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. 159184
    Prev
    Next
    INDEX
    Explanations

    furniture, attractions, items

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

    advantages over

    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
     Belize
    0.47
    एको
    0.47
    краё
    0.46
     Puerto
    0.45
    Is
    0.45
    複数
    0.44
     Ironman
    0.44
    ጂ
    0.44
    нансо
    0.44
     Djibouti
    0.43
    POSITIVE LOGITS
     خیال
    0.45
    시켜
    0.44
     주제
    0.42
     pozorn
    0.42
     내용을
    0.42
    겅
    0.42
     συν
    0.42
     rằng
    0.42
     காட்ச
    0.42
    emis
    0.42
    Activations Density 0.000%

    No Known Activations