© 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. 84220
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     of
    -1.38
    ="
    -1.18
    を
    -1.17
    *
    -1.12
    >
    -1.11
    ,
    -1.09
    '
    -1.08
     book
    -1.08
    :
    -1.07
    などが
    -1.05
    POSITIVE LOGITS
    imanapun
    1.29
    Slav
    1.29
    どれだけ
    1.25
    Indien
    1.23
    Nieuw
    1.23
    Hilsen
    1.20
    Pá
    1.19
    Missi
    1.19
    چنین
    1.18
    Ÿ
    1.16
    Activations Density 0.000%

    No Known Activations