© 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. 155035
    Prev
    Next
    INDEX
    Explanations

    willing to insert, device insertion

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

    multilingual concepts and states

    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
    लु
    0.53
    PAR
    0.49
    וח
    0.48
    ।
    0.48
    DAR
    0.46
    ק
    0.46
    עם
    0.45
    ।"
    0.45
    রাশ
    0.45
    Armstrong
    0.44
    POSITIVE LOGITS
     joie
    0.59
     mittlerweile
    0.54
     ahora
    0.53
     opleiding
    0.52
     nyní
    0.52
     agora
    0.51
     dnes
    0.51
     cession
    0.50
     mise
    0.50
     lohnt
    0.50
    Activations Density 0.002%

    No Known Activations