© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57452
    Prev
    Next
    INDEX
    Explanations

    physical damage or failure

    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
     برای
    -0.99
     для
    -0.98
    しっかり
    -0.95
     отредакти
    -0.93
    BOURNE
    -0.91
     одновременно
    -0.90
     glistening
    -0.89
    ޚ
    -0.87
    つもり
    -0.85
     pietre
    -0.85
    POSITIVE LOGITS
     due
    1.88
     or
    1.77
     when
    1.63
     from
    1.49
     under
    1.45
     during
    1.41
     and
    1.29
     debido
    1.27
     after
    1.07
     on
    1.04
    Activations Density 0.065%

    No Known Activations