© 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. 250425
    Prev
    Next
    INDEX
    Explanations

    business products

    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
    Negative Logits
     аудио
    0.55
     incidente
    0.55
     effetti
    0.54
    ເກ
    0.54
     hô
    0.53
    AUDIO
    0.52
    ﮕ
    0.52
    BOX
    0.52
    +)
    0.51
    <bos>
    0.50
    POSITIVE LOGITS
     dystrophy
    0.49
    áz
    0.46
    unos
    0.46
    ua
    0.45
    iness
    0.43
     نسخ
    0.42
    ázat
    0.42
     Pennsylvania
    0.42
     housework
    0.41
     Maryland
    0.40
    Activations Density 0.000%

    No Known Activations