© 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. 66909
    Prev
    Next
    INDEX
    Explanations

    is connected to

    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
     to
    -1.87
     where
    -1.85
    これは
    -1.51
     not
    -1.41
    这个
    -1.37
    這個
    -1.34
    はこの
    -1.31
     how
    -1.27
     now
    -1.25
    cznym
    -1.25
    POSITIVE LOGITS
     redé
    1.31
     my
    1.31
     hermosos
    1.25
     résine
    1.25
    ῥ
    1.23
    unding
    1.22
    ņi
    1.22
     empê
    1.20
     coussin
    1.20
     lô
    1.20
    Activations Density 0.364%

    No Known Activations