© 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. 227036
    Prev
    Next
    INDEX
    Explanations

    otherwise colorless

    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
    س
    0.50
     discíp
    0.47
    Thumbnail
    0.47
     प्रैक्टिस
    0.45
     deshalb
    0.45
     randomIndex
    0.45
    Revised
    0.44
    Pues
    0.44
    TextBox
    0.43
     пыта
    0.43
    POSITIVE LOGITS
    thus
    0.53
     wrongdoing
    0.49
    することで
    0.49
     astfel
    0.47
    ))$.
    0.46
    担保
    0.45
    শিদ
    0.44
     committing
    0.44
    とのこと
    0.44
    ignant
    0.44
    Activations Density 0.002%

    No Known Activations