© 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. 128954
    Prev
    Next
    INDEX
    Explanations

    separates, specific, realistic

    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
    ﺎ
    0.46
     tiennent
    0.45
     châ
    0.44
     élu
    0.44
     serve
    0.44
    সি
    0.44
     rendent
    0.44
    い
    0.43
    ran
    0.43
     rendre
    0.43
    POSITIVE LOGITS
    iędzy
    0.46
    not
    0.45
    prior
    0.45
    i
    0.45
     Zapata
    0.45
    yrs
    0.44
    speaker
    0.43
    zenesulf
    0.43
    ideo
    0.42
     Langevin
    0.42
    Activations Density 0.001%

    No Known Activations