© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109745
    Prev
    Next
    INDEX
    Explanations

    original value/hype

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colouring
    0.47
    ᓘ
    0.47
    ውነተኛ
    0.46
    سک
    0.45
     secretion
    0.44
     détour
    0.43
     secretions
    0.42
     embarrassing
    0.42
     critical
    0.42
     приветствую
    0.41
    POSITIVE LOGITS
    ;
    0.49
    <0x0D>
    0.48
    rapers
    0.47
    September
    0.47
    article
    0.46
    elesa
    0.45
        
    0.45
    SCHRAMM
    0.44
    UGUST
    0.44
    Rec
    0.43
    Activations Density 0.007%

    No Known Activations