© 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. 41119
    Prev
    Next
    INDEX
    Explanations

    ids in code or data structures

    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
    They
    -2.42
    These
    -2.13
    Since
    -2.05
    Through
    -2.05
    When
    -2.03
    With
    -2.00
     έχει
    -1.97
     them
    -1.93
    While
    -1.92
    Usually
    -1.91
    POSITIVE LOGITS
    鸲
    1.63
    醅
    1.60
    sekret
    1.52
     cobra
    1.52
    rii
    1.48
     juſ
    1.48
    OfWork
    1.44
    ’
    1.43
     gustar
    1.40
    CHANG
    1.38
    Activations Density 0.026%

    No Known Activations