© 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. 58192
    Prev
    Next
    INDEX
    Explanations

    defining functions or variables

    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
    それが
    -1.44
     it
    -1.31
     others
    -1.24
     which
    -1.14
    それを
    -1.13
     ולה
    -1.09
     этого
    -1.07
     beziehungs
    -1.00
    two
    -1.00
     которые
    -0.99
    POSITIVE LOGITS
     the
    2.17
     any
    1.45
     км
    1.24
     a
    1.16
     algún
    1.13
     used
    1.13
     obtained
    1.11
     shorthand
    1.09
     our
    1.09
     defined
    1.06
    Activations Density 0.059%

    No Known Activations