© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43546
    Prev
    Next
    INDEX
    Explanations

    words starting with ref

    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
    iocene
    -2.30
    ᨈ
    -2.13
    ünster
    -2.08
     diminutive
    -2.06
     když
    -2.02
    ↵↵
    -1.99
    AS
    -1.98
     ولكن
    -1.91
    で
    -1.90
    𖤍
    -1.90
    POSITIVE LOGITS
    橚
    2.81
    蛲
    2.78
    鶺
    2.48
     Mesin
    2.45
     Masuk
    2.20
     illustratie
    2.20
    絎
    2.20
     parachoque
    2.14
    Ꭳ
    2.13
    媜
    2.08
    Activations Density 0.014%

    No Known Activations