© 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. 47307
    Prev
    Next
    INDEX
    Explanations

    running distances and times

    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
    分か
    -0.84
    값
    -0.76
     abortions
    -0.75
    Agenda
    -0.73
     ordination
    -0.73
     symbo
    -0.72
    lichkeit
    -0.71
     Rada
    -0.71
    ystems
    -0.70
     condens
    -0.70
    POSITIVE LOGITS
    coledì
    0.86
    comune
    0.86
     move
    0.81
    راهيم
    0.79
    verständlich
    0.77
     tausend
    0.74
     wszel
    0.74
     difficulties
    0.73
     obstacles
    0.71
    gpl
    0.71
    Activations Density 0.025%

    No Known Activations