© 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-16K
    7. 12419
    Prev
    Next
    INDEX
    Explanations

    react imports from 'react'

    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_16k_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
    ગ
    0.45
    ゴ
    0.44
    蒡
    0.42
    اني
    0.41
     combos
    0.40
    о
    0.39
     bai
    0.39
     inp
    0.39
    نم
    0.39
    煸
    0.39
    POSITIVE LOGITS
    photo
    0.47
    compliant
    0.44
     αλλά
    0.43
    uron
    0.43
    עים
    0.43
    picture
    0.42
    λεί
    0.42
    breve
    0.42
    recovered
    0.42
    حصل
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.