© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113226
    Prev
    Next
    INDEX
    Explanations

    HTML class attributes

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

    the "class" attribute in HTML div tags.

    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
     was
    -1.55
    が使
    -1.44
     mocy
    -1.44
     wysokiej
    -1.37
     
    -1.33
    },
    -1.33
     needs
    -1.29
     araştır
    -1.29
     nivå
    -1.28
     především
    -1.28
    POSITIVE LOGITS
     to
    1.48
     ""],
    1.45
     geheim
    1.37
    ileri
    1.36
     such
    1.34
     چیست
    1.32
    ”،
    1.31
    NUMX
    1.27
    gamer
    1.25
    such
    1.23
    Activations Density 0.008%

    No Known Activations