© 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. 14860
    Prev
    Next
    INDEX
    Explanations

    found people, bodies, or objects

    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
     (
    -1.06
     for
    -1.01
    -
    -0.99
     bleiben
    -0.95
    庚
    -0.92
     devraient
    -0.92
    :=
    -0.90
     frågan
    -0.88
     выстав
    -0.87
     unsatisfied
    -0.87
    POSITIVE LOGITS
     found
    1.30
    找到
    1.25
    Only
    1.20
     setelah
    1.19
     raggiunto
    1.18
     after
    1.17
    After
    1.16
     alugar
    1.13
     trovato
    1.13
     удалось
    1.10
    Activations Density 0.031%

    No Known Activations