© 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. 128928
    Prev
    Next
    INDEX
    Explanations

    location

    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
     ก็
    -1.52
     усилия
    -1.52
    Here
    -1.50
    ;
    -1.48
    Ᏺ
    -1.48
    籥
    -1.46
    买了
    -1.44
     Begriffe
    -1.41
    躄
    -1.40
     também
    -1.39
    POSITIVE LOGITS
     it
    2.03
     else
    1.80
     we
    1.39
    hermoso
    1.24
     those
    1.24
    xca
    1.23
     باشید
    1.22
     averse
    1.22
     compréhen
    1.20
    Ŏ
    1.20
    Activations Density 0.018%

    No Known Activations