© 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. 34273
    Prev
    Next
    INDEX
    Explanations

    Oxidation, Starbucks, Walter Scott

    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
     ristorante
    -1.11
    StandardCharsets
    -1.07
     campe
    -1.07
     espet
    -1.06
     Brasile
    -1.06
    länger
    -1.05
     солнца
    -1.05
     llor
    -1.04
    chuhe
    -1.04
     lorsqu
    -1.04
    POSITIVE LOGITS
     expresó
    1.17
     requerida
    1.16
     melhorar
    1.13
     preferências
    1.12
     acepción
    1.10
     τῶν
    1.10
     estremamente
    1.10
    zdroj
    1.09
     fatores
    1.09
     они
    1.08
    Activations Density 0.001%

    No Known Activations