© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67740
    Prev
    Next
    INDEX
    Explanations

    NEVER SUBMIT

    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
    Leírás
    -1.60
     великолеп
    -1.48
    Kelebihan
    -1.45
    Szer
    -1.45
     SAYS
    -1.42
    Descriere
    -1.40
    Kenapa
    -1.38
    maining
    -1.37
    antaranya
    -1.36
    Sekarang
    -1.36
    POSITIVE LOGITS
    !
    1.90
    —
    1.83
    "
    1.78
    ?
    1.71
    </b>
    1.57
    ”
    1.49
    (
    1.45
    <
    1.38
    .”
    1.37
    )
    1.37
    Activations Density 0.511%

    No Known Activations