© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127271
    Prev
    Next
    INDEX
    Explanations

    The present disclosure or specification

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

    concepts and domains

    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
     ডেকে
    0.46
     जिनसे
    0.45
    গণ
    0.44
     तल
    0.42
     perpend
    0.42
    
    0.42
     हथ
    0.41
     ObjData
    0.40
    رځ
    0.40
     lettres
    0.39
    POSITIVE LOGITS
     cosmology
    0.50
    -
    0.46
     webinar
    0.46
    channel
    0.46
    sizeof
    0.45
    bir
    0.45
    postId
    0.44
    bomb
    0.44
    language
    0.44
     sanit
    0.43
    Activations Density 0.002%

    No Known Activations