© 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. 10948
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    topics and descriptions

    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
     hilfre
    0.48
     मैले
    0.42
     Jolla
    0.41
     déprimées
    0.40
     pptn
    0.39
    piej
    0.37
     spezielle
    0.36
    <unused254>
    0.36
     ainfi
    0.36
     considerar
    0.36
    POSITIVE LOGITS
     la
    0.39
    ன்மை
    0.38
     DE
    0.36
     l
    0.35
    webpack
    0.35
    রাজ
    0.35
    檤
    0.35
    de
    0.35
    업
    0.35
    处理器
    0.34
    Activations Density 0.233%

    No Known Activations