© 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. 80804
    Prev
    Next
    INDEX
    Explanations

    ownership, clarity, control

    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
    Negative Logits
    Verm
    0.51
    Generalized
    0.47
    Visit
    0.46
     Component
    0.43
    Generated
    0.43
     Err
    0.42
     Generalized
    0.42
    钡
    0.42
    Modify
    0.42
    Results
    0.41
    POSITIVE LOGITS
     feta
    0.52
    borough
    0.50
     atractivo
    0.46
    vé
    0.43
    nds
    0.42
     annoncé
    0.42
    凄
    0.41
     votos
    0.41
     lado
    0.41
    pageY
    0.41
    Activations Density 0.004%

    No Known Activations