© 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. 128762
    Prev
    Next
    INDEX
    Explanations

    most important

    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
     also
    -1.34
     and
    -1.26
     szint
    -1.21
    óis
    -1.12
    সূত্র
    -1.07
    ULTURA
    -1.05
     también
    -1.05
    たん
    -1.03
     такие
    -1.01
    also
    -1.00
    POSITIVE LOGITS
     any
    1.74
     anyone
    1.51
     anybody
    1.27
     anything
    1.23
    izational
    1.23
     of
    1.19
    ebly
    1.18
     this
    1.13
     about
    1.11
     autonomia
    1.09
    Activations Density 0.036%

    No Known Activations