© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11264
    Prev
    Next
    INDEX
    Explanations

    code filenames and identifiers

    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
     ktoré
    -1.24
     This
    -1.21
     THIS
    -1.18
     Před
    -1.15
     There
    -1.15
     THERE
    -1.12
    に向かって
    -1.06
    ervations
    -1.05
     Both
    -1.05
     jeżeli
    -1.04
    POSITIVE LOGITS
    <bos>
    1.16
    2
    1.13
    3
    1.03
    0
    1.02
    する
    0.98
     distru
    0.96
     platy
    0.96
     mortgagee
    0.95
    を
    0.95
     with
    0.93
    Activations Density 0.001%

    No Known Activations