© 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. 22-GEMMASCOPE-RES-131K
    7. 65291
    Prev
    Next
    INDEX
    Explanations

    method chaining and callbacks

    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_22/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
     their
    -1.58
     one
    -1.53
     any
    -1.48
     from
    -1.44
     at
    -1.44
     and
    -1.43
     Many
    -1.36
     When
    -1.30
     If
    -1.27
     your
    -1.26
    POSITIVE LOGITS
     kula
    1.34
    vereign
    1.30
     nonostante
    1.30
    これは
    1.27
     koi
    1.25
     burch
    1.23
     uan
    1.23
     lagos
    1.22
    それは
    1.20
     cæ
    1.19
    Activations Density 0.003%

    No Known Activations