© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62716
    Prev
    Next
    INDEX
    Explanations

    halting operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eerste
    -0.90
     verità
    -0.83
    jin
    -0.82
     your
    -0.80
    rah
    -0.76
     rechazo
    -0.76
    ::*;
    -0.76
     THRO
    -0.76
     manquer
    -0.76
     börjar
    -0.75
    POSITIVE LOGITS
     completely
    1.38
     навсегда
    1.13
     altogether
    1.10
     prematurely
    1.09
     Completely
    1.08
    completely
    1.03
     cleanly
    1.01
     vĩnh
    1.01
     except
    0.98
     abruptly
    0.96
    Activations Density 0.093%

    No Known Activations