© 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. 80381
    Prev
    Next
    INDEX
    Explanations

    companies, employers, groups

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

    depending on

    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
    மது
    0.49
     postępow
    0.46
    जारत
    0.44
     पंचायत
    0.42
    !”
    0.41
    사를
    0.41
     WEST
    0.41
    𝕂
    0.41
    अनु
    0.40
     that
    0.40
    POSITIVE LOGITS
     円
    0.48
     명
    0.48
    iend
    0.46
    ータ
    0.45
     來
    0.45
     podendo
    0.44
     નથી
    0.44
    ビング
    0.44
     ɔ
    0.44
    ارع
    0.44
    Activations Density 0.001%

    No Known Activations