© 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. 36572
    Prev
    Next
    INDEX
    Explanations

    inner pulp, bear markets, polar molecules

    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
     Atlantis
    0.44
     impossible
    0.37
     types
    0.37
    respon
    0.36
     Impossible
    0.36
    ese
    0.36
    <start_of_image>
    0.36
    esian
    0.35
     Cream
    0.35
     Hel
    0.34
    POSITIVE LOGITS
    .
    0.44
    သက်
    0.38
     którą
    0.38
     ips
    0.38
     Tava
    0.38
    ﾄ
    0.37
     właścic
    0.37
     wcześ
    0.37
     veterinarian
    0.37
     propriétaire
    0.37
    Activations Density 0.000%

    No Known Activations