© 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. 65340
    Prev
    Next
    INDEX
    Explanations

    code declarations and structures

    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
    ！！
    -1.23
    ！！！
    -1.21
     those
    -1.18
    !!!!
    -1.10
    nější
    -1.09
    !!!!!
    -1.09
     Terkait
    -1.07
     virtudes
    -1.05
     allows
    -1.03
    Taking
    -1.01
    POSITIVE LOGITS
     wonderful
    1.22
     fabulous
    1.20
     exceedingly
    1.18
     molti
    1.18
     extremely
    1.17
     prides
    1.16
     kinda
    1.16
     delightful
    1.13
     startling
    1.11
     Dinas
    1.11
    Activations Density 0.005%

    No Known Activations