© 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. 21248
    Prev
    Next
    INDEX
    Explanations

    BIOS settings, subsurface geology

    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
    「
    -2.86
     ravaged
    -2.61
    鹮
    -2.44
    t
    -2.39
    不仅仅
    -2.27
    你
    -2.27
    ла
    -2.25
     FIVE
    -2.23
    Ꮅ
    -2.20
     MUCH
    -2.17
    POSITIVE LOGITS
    しようと
    2.61
    逦
    2.25
    してます
    2.23
    rencies
    2.22
    王的
    2.17
    礎
    2.13
    يقة
    2.11
    したもの
    2.06
    いただきました
    2.05
     сможет
    2.05
    Activations Density 0.004%

    No Known Activations