© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129725
    Prev
    Next
    INDEX
    Explanations

    exist only, number of, source of

    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
     sentí
    -1.36
     encontré
    -1.20
     duele
    -1.17
     pregunto
    -1.13
     obstante
    -1.12
     PartialEq
    -1.10
     menyesuaikan
    -1.10
    veloper
    -1.10
    šana
    -1.05
     dimentic
    -1.05
    POSITIVE LOGITS
     poto
    1.11
     mets
    1.11
     dsp
    1.06
     disgra
    1.04
     abomin
    1.02
     adal
    1.00
    lepiej
    0.98
    ̔
    0.98
     È
    0.97
     traged
    0.96
    Activations Density 0.044%

    No Known Activations