© 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. 232345
    Prev
    Next
    INDEX
    Explanations

    following language-specific 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
    ing
    0.54
     combat
    0.52
    ac
    0.50
    荒
    0.47
    msg
    0.45
    urers
    0.44
    combat
    0.44
    airs
    0.42
    자
    0.42
    can
    0.41
    POSITIVE LOGITS
     fechas
    0.55
    larım
    0.50
     Entscheid
    0.50
     উপরে
    0.50
    ບໍ່
    0.50
    সমূ
    0.50
    மில்
    0.49
    ভাঁ
    0.49
     Música
    0.49
     सुशील
    0.49
    Activations Density 0.000%

    No Known Activations