© 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. 71929
    Prev
    Next
    INDEX
    Explanations

    http/https web addresses

    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
    结语
    -1.32
     where
    -1.26
     familia
    -1.24
    ？』
    -1.23
    </h2>
    -1.23
    方針
    -1.20
    そのため
    -1.18
    ’，
    -1.17
    ？（
    -1.17
    ्टर
    -1.16
    POSITIVE LOGITS
    為に
    1.49
    ほら
    1.43
     \
    1.43
    が可能
    1.41
    にします
    1.39
    感を
    1.39
    ことも
    1.38
    づけ
    1.38
    様な
    1.36
    の方に
    1.36
    Activations Density 0.023%

    No Known Activations