© 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. 112934
    Prev
    Next
    INDEX
    Explanations

    disease, weight, system, card

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

    terms related to physical measurements like "body weight" or identifying medical conditions and disorders.

    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
     ErrInvalid
    -1.42
     these
    -1.36
    こんばん
    -1.34
    こんに
    -1.30
     Leur
    -1.28
    国家的
    -1.23
    Прода
    -1.22
     poleg
    -1.22
     contains
    -1.21
     Personne
    -1.20
    POSITIVE LOGITS
    戗
    1.59
    й
    1.53
    Hilsen
    1.51
    VILLE
    1.48
    izzazione
    1.45
    alucía
    1.45
    皤
    1.43
    地说道
    1.41
    leştir
    1.39
    orative
    1.34
    Activations Density 0.268%

    No Known Activations