© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110773
    Prev
    Next
    INDEX
    Explanations

    scientific concepts and terms

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

    concepts related to effects, outcomes, or results produced by something.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     bret
    -1.20
     each
    -1.18
     from
    -1.11
     xperia
    -1.11
     каждого
    -1.11
     œ
    -1.10
     xvii
    -1.08
     ‚
    -1.08
    __;
    -1.07
     VERT
    -1.06
    POSITIVE LOGITS
     only
    1.80
     or
    1.68
     that
    1.59
     đị
    1.48
     other
    1.48
     atacado
    1.41
     almohada
    1.40
     alér
    1.38
     specific
    1.38
     restricting
    1.37
    Activations Density 0.489%

    No Known Activations