© 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. 18817
    Prev
    Next
    INDEX
    Explanations

    numbers following "question"

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

    change actions and habits

    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
     المصفوفه
    0.52
    বাদিক
    0.50
    র্ধ্ব
    0.48
    㧕
    0.47
     बेंगल
    0.47
     вікі
    0.47
     simonsen
    0.47
     방정식
    0.46
    𝐰
    0.45
    IGATION
    0.45
    POSITIVE LOGITS
    ipi
    0.49
     ‘
    0.46
    <0xC2>
    0.45
    po
    0.44
    市
    0.43
    <em>
    0.43
    pl
    0.43
     lm
    0.42
    <0xE2>
    0.42
    plr
    0.41
    Activations Density 0.000%

    No Known Activations