© 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. 25411
    Prev
    Next
    INDEX
    Explanations

    study / research papers

    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
    -1.74
     if
    -1.61
     also
    -1.59
     even
    -1.59
     EVERY
    -1.31
     before
    -1.30
     will
    -1.28
     or
    -1.25
     at
    -1.24
     Also
    -1.18
    POSITIVE LOGITS
     venit
    1.27
     protesta
    1.23
     evidente
    1.23
     idee
    1.18
    再一次
    1.17
     boister
    1.16
     mediante
    1.14
    籥
    1.14
     magnific
    1.13
     domina
    1.13
    Activations Density 0.005%

    No Known Activations