© 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. 10-GEMMASCOPE-RES-131K
    7. 102842
    Prev
    Next
    INDEX
    Explanations

    clearly obvious statements

    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_10/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
     Another
    -1.38
     Также
    -1.27
     ternyata
    -1.26
    😦
    -1.26
    ESSA
    -1.24
     psychologie
    -1.23
     Administração
    -1.23
     Except
    -1.22
     pastikan
    -1.22
     ་
    -1.21
    POSITIVE LOGITS
     different
    1.38
     związane
    1.28
     apsau
    1.27
     kiek
    1.24
     mocno
    1.22
     bedeckt
    1.21
     بهداشتی
    1.21
     äußerst
    1.17
     which
    1.16
     obvious
    1.16
    Activations Density 0.036%

    No Known Activations