© 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. 40-GEMMASCOPE-2-RES-262K
    7. 215270
    Prev
    Next
    INDEX
    Explanations

    potential connection

    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_40_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
    ⎙
    0.42
    ík
    0.40
    uft
    0.38
    abhas
    0.37
    orphan
    0.37
     आग
    0.36
     cavitation
    0.36
    
    0.36
    lük
    0.36
    ===
    0.36
    POSITIVE LOGITS
    ष
    0.44
     delicios
    0.42
     maravilh
    0.41
     zároveň
    0.40
     jednocześnie
    0.40
     maravilloso
    0.39
     одновременно
    0.38
     marvellous
    0.38
     Moses
    0.37
    covariance
    0.37
    Activations Density 0.000%

    No Known Activations