© 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. 43956
    Prev
    Next
    INDEX
    Explanations

    stream and creek

    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
     a
    -1.62
    КС
    -1.59
     frança
    -1.59
     officielles
    -1.52
    𓆏
    -1.50
     publiques
    -1.49
    astos
    -1.48
    ⢪
    -1.47
     própri
    -1.47
    zember
    -1.46
    POSITIVE LOGITS
     or
    1.98
     profundas
    1.54
     żołnier
    1.53
     χαρα
    1.48
    )
    1.47
     vectoriales
    1.44
     consideradas
    1.43
    ."
    1.42
     raras
    1.40
     beauti
    1.38
    Activations Density 0.021%

    No Known Activations