© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 633
    Prev
    Next
    INDEX
    Explanations

    SQL id column

    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
    y
    -1.52
    毉
    -1.50
    ons
    -1.46
     largely
    -1.43
     the
    -1.42
     crappy
    -1.30
    sed
    -1.30
    戋
    -1.30
    </h2>
    -1.28
    generally
    -1.28
    POSITIVE LOGITS
     було
    1.63
    咎
    1.53
    怪我
    1.45
    ньому
    1.44
     it
    1.41
    飢
    1.30
    Ĉ
    1.27
    égio
    1.27
     bylo
    1.27
    }(\
    1.26
    Activations Density 0.037%

    No Known Activations