© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4733
    Prev
    Next
    INDEX
    Explanations

    proper nouns like Tiber, Leo, E

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    t
    0.52
    to
    0.42
    it
    0.40
    in
    0.38
    tt
    0.38
    ti
    0.37
    of
    0.36
    i
    0.36
     be
    0.35
    ก
    0.35
    POSITIVE LOGITS
    :
    0.52
    ের
    0.30
    }:
    0.30
     ebben
    0.29
    cession
    0.28
    0.27
    的过程中
    0.26
    의
    0.26
     mischievous
    0.26
    اموش
    0.26
    Activations Density 0.173%

    No Known Activations