© 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. 39024
    Prev
    Next
    INDEX
    Explanations

    Florence Hartmann

    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
    Elke
    -1.09
    *-*-
    -1.05
     on
    -1.05
    Ирина
    -1.03
    大爷
    -1.02
    ☆☆☆☆
    -1.01
     lievito
    -1.01
    呐
    -1.00
     zelfs
    -0.99
    cznej
    -0.99
    POSITIVE LOGITS
     composé
    1.24
    porus
    1.15
    Чыганаклар
    1.13
     části
    1.13
     what
    1.11
    𝑞
    1.11
     kathol
    1.10
    филь
    1.09
     τὴν
    1.09
     Heilige
    1.09
    Activations Density 0.021%

    No Known Activations