© 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. 192294
    Prev
    Next
    INDEX
    Explanations

    powerful CPU, legitimately seeking

    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
    繃
    0.45
    ڎ
    0.44
    $/../../
    0.42
    laughs
    0.39
    ারে
    0.39
    dzie
    0.38
    ahuasca
    0.38
    әү
    0.37
    谄
    0.36
    iooni
    0.36
    POSITIVE LOGITS
     non
    0.43
     char
    0.39
     erase
    0.39
     Non
    0.38
     erfolgte
    0.38
     Pages
    0.37
     mac
    0.37
     sofr
    0.37
     fue
    0.37
     band
    0.36
    Activations Density 0.000%

    No Known Activations