© 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. 195288
    Prev
    Next
    INDEX
    Explanations

    Gran or Henry or The or Philip

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

    historical dates and events

    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
     nėra
    0.52
     précédent
    0.49
     කරයි
    0.48
     বাহিরে
    0.45
     fría
    0.44
     (°
    0.44
     températures
    0.43
    룹
    0.43
    鸫
    0.43
    ◠
    0.42
    POSITIVE LOGITS
     feminine
    0.44
     carefully
    0.44
     creativity
    0.44
     complete
    0.44
     relativity
    0.44
    ethod
    0.42
    ர்த்த
    0.41
     concept
    0.40
    得了
    0.40
     entirely
    0.40
    Activations Density 0.002%

    No Known Activations