© 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. 10-GEMMASCOPE-RES-131K
    7. 1367
    Prev
    Next
    INDEX
    Explanations

    acro-

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to acrobatics and gymnastic movements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    \
    -3.41
    '
    -2.92
    >
    -2.66
    c
    -2.44
     &
    -2.17
    =
    -2.17
    -
    -2.14
    2
    -2.09
    (
    -2.08
    /
    -2.06
    POSITIVE LOGITS
    ?”
    2.33
    Ꮂ
    2.28
     Esatti
    2.27
    "),
    2.20
    ୬
    2.17
    '),
    2.14
    ꪔ
    2.09
     considérons
    2.05
    ználat
    2.03
    ⮜
    2.03
    Activations Density 0.007%

    No Known Activations