© 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. 66150
    Prev
    Next
    INDEX
    Explanations

    degree or intensity

    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
     of
    -1.68
     it
    -1.48
     these
    -1.20
     there
    -1.19
     that
    -1.16
    ݣ
    -1.16
    ◆◇
    -1.16
     prevista
    -1.13
    ные
    -1.13
     柱
    -1.12
    POSITIVE LOGITS
     more
    1.58
     enough
    1.45
     beaucoup
    1.39
     greatly
    1.34
     mucho
    1.30
     molto
    1.30
     dearly
    1.30
     much
    1.29
     enorm
    1.28
     mycket
    1.25
    Activations Density 0.054%

    No Known Activations