© 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. 123869
    Prev
    Next
    INDEX
    Explanations

    Q: or Hand:

    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_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
     "
    -2.61
    颙
    -2.39
     is
    -2.36
     Füßen
    -2.30
    肫
    -2.17
    The
    -2.17
    觏
    -2.11
    </h5>
    -2.09
    蓦
    -2.09
     इस
    -2.08
    POSITIVE LOGITS
    to
    3.03
    8
    2.81
    5
    2.63
     puteți
    2.47
     Какой
    2.45
     utilizz
    2.44
    from
    2.38
    事は
    2.36
     Какие
    2.33
    使う
    2.28
    Activations Density 0.000%

    No Known Activations