© 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. 220074
    Prev
    Next
    INDEX
    Explanations

    interests, password, dedicated

    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
     wrinkles
    0.41
     youth
    0.39
     wrinkled
    0.38
    ᷅
    0.38
     nggak
    0.38
     peuple
    0.37
     arable
    0.37
    "!
    0.36
     linii
    0.36
     likeness
    0.35
    POSITIVE LOGITS
     Wizards
    0.39
     Kilometer
    0.39
     Zaj
    0.39
    ста
    0.38
     fiber
    0.38
    olev
    0.37
    fiber
    0.36
     Lichtenfels
    0.35
    佩
    0.35
     komple
    0.35
    Activations Density 0.000%

    No Known Activations