© 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. 64783
    Prev
    Next
    INDEX
    Explanations

    championship results or rankings

    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
    -1.20
    :
    -1.09
     and
    -1.09
     including
    -1.06
    including
    -1.02
     員
    -1.00
     or
    -0.97
     (
    -0.96
    $\
    -0.94
    {

    -0.94
    POSITIVE LOGITS
     feroit
    1.21
     fera
    1.16
     âme
    1.13
     remé
    1.13
     marad
    1.13
    skrä
    1.12
     saurait
    1.09
     bacté
    1.09
     veu
    1.06
     situe
    1.05
    Activations Density 0.068%
    No Known Activations