© 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. 10-GEMMASCOPE-RES-131K
    7. 100836
    Prev
    Next
    INDEX
    Explanations

    links to domains

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

    the string "://" which appears in URLs and web protocols.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    _
    -1.70
    啬
    -1.66
    穽
    -1.64
    specifically
    -1.60
    ໊
    -1.55
     hiér
    -1.52
     inauguración
    -1.52
    katapos
    -1.51
     nabízí
    -1.49
    ꜆
    -1.48
    POSITIVE LOGITS
    褔
    2.00
     with
    1.70
    bollah
    1.50
     σε
    1.48
     …”
    1.42
    rschein
    1.41
     also
    1.41
    कि
    1.37
    стьян
    1.37
    彼は
    1.36
    Activations Density 0.042%

    No Known Activations