© 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. 58084
    Prev
    Next
    INDEX
    Explanations

    accusations or origin

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

    technical or data processing terms

    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
     clapping
    0.43
     mastect
    0.42
     alkyl
    0.41
    𝕂
    0.41
     coisas
    0.41
     mencionó
    0.41
     dentées
    0.41
    رجال
    0.41
     prerog
    0.40
     ženy
    0.40
    POSITIVE LOGITS
     ומ
    0.52
     במהלך
    0.50
    ཚ
    0.50
     את
    0.49
     וא
    0.48
     בי
    0.47
     וה
    0.47
     richly
    0.46
     சதவீ
    0.46
    localized
    0.46
    Activations Density 0.000%

    No Known Activations