© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11626
    Prev
    Next
    INDEX
    Explanations

    code snippets and addresses

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

    numerical identifiers or version numbers, particularly those following underscores or in structured naming conventions.

    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
    </h3>
    -2.97
     seems
    -2.64
     was
    -2.42
    ؛
    -2.41
     appears
    -2.28
     unquestionably
    -2.28
     anún
    -2.20
     know
    -2.02
     implementar
    -2.02
    !”
    -1.95
    POSITIVE LOGITS
    </b>
    3.64
    3
    2.41
    9
    2.30
    犼
    2.28
     umgeben
    2.28
    4
    2.16
    5
    2.11
     remporté
    2.11
     culmination
    2.09
     augmenté
    2.06
    Activations Density 0.103%

    No Known Activations