© 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. 117093
    Prev
    Next
    INDEX
    Explanations

    lists following specific conditions

    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
     yaptığı
    -1.19
    %，
    -1.15
    ``,
    -1.13
     to
    -1.05
     sposob
    -1.04
     kommende
    -1.02
    ]$,
    -0.99
    erunner
    -0.99
     who
    -0.98
     infancia
    -0.98
    POSITIVE LOGITS
     was
    1.80
     were
    1.77
     is
    1.59
     occurred
    1.44
     there
    1.43
     are
    1.43
     has
    1.38
     have
    1.37
     occurs
    1.36
     happened
    1.32
    Activations Density 0.291%

    No Known Activations