© 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. 57125
    Prev
    Next
    INDEX
    Explanations

    maximum values

    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
    despite
    -1.34
    gives
    -1.33
     unbelievably
    -1.31
     diversos
    -1.31
    mainly
    -1.30
    鴴
    -1.27
     deliciously
    -1.27
    presumably
    -1.27
    immediately
    -1.26
     delightfully
    -1.26
    POSITIVE LOGITS
     possible
    2.27
     allowable
    1.86
     allowed
    1.75
     of
    1.58
     permissible
    1.57
     sustainable
    1.56
     that
    1.52
     allow
    1.44
     attainable
    1.41
    可能的
    1.38
    Activations Density 0.023%

    No Known Activations