© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117776
    Prev
    Next
    INDEX
    Explanations

    according to

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

    distance, resolution, time, languages, deep

    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
    Coef
    0.55
    𝒹
    0.50
    責任
    0.46
    唁
    0.44
    कोल
    0.44
    🆁
    0.44
    ствует
    0.44
    :]:
    0.44
    ಾಯ
    0.44
    鐲
    0.44
    POSITIVE LOGITS
     Nigerian
    0.47
    Nigerian
    0.44
     crashed
    0.44
    turning
    0.43
    us
    0.41
     fiercely
    0.41
     některé
    0.41
     known
    0.41
    开始了
    0.40
     Year
    0.40
    Activations Density 0.000%

    No Known Activations