© 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. 85797
    Prev
    Next
    INDEX
    Explanations

    XML/HTML tags and attributes

    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
     to
    -1.70
     newfound
    -1.55
     étrange
    -1.52
     kartą
    -1.48
     istor
    -1.48
    镠
    -1.46
     jugó
    -1.46
    Razer
    -1.45
    Masukkan
    -1.45
     adverten
    -1.42
    POSITIVE LOGITS
    —
    1.63
    ?
    1.60
    ´
    1.59
    .
    1.58
    i
    1.53
    it
    1.52
    …
    1.52
    ."
    1.52
     was
    1.48
    on
    1.43
    Activations Density 0.254%

    No Known Activations