© 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. 215403
    Prev
    Next
    INDEX
    Explanations

    sequential components or actions

    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
    Negative Logits
    ync
    0.42
    8
    0.42
    ktops
    0.42
    affichage
    0.40
     lingu
    0.40
    iar
    0.39
    nikiem
    0.39
     £
    0.39
    git
    0.38
    9
    0.38
    POSITIVE LOGITS
     участь
    0.43
     Promised
    0.43
     द्वीप
    0.42
     harnessed
    0.38
    Waiting
    0.38
    協力
    0.38
     Pandemic
    0.38
    唑
    0.37
     уча
    0.37
     prioritized
    0.37
    Activations Density 0.000%

    No Known Activations