© 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. 129002
    Prev
    Next
    INDEX
    Explanations

    describes weak states

    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
    .
    -2.59
    逦
    -2.58
    찮
    -2.25
     Auftritt
    -2.20
     individuellen
    -2.14
    好像是
    -2.13
    dized
    -2.05
     zimní
    -2.03
    玬
    -2.03
     can
    -1.98
    POSITIVE LOGITS
     ſch
    2.56
    焢
    2.34
     美甲
    2.33
    s
    2.22
    蹀
    2.16
    dámské
    2.16
    踅
    2.14
    anın
    2.08
    躡
    2.05
     camiset
    1.99
    Activations Density 0.001%

    No Known Activations