© 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. 40440
    Prev
    Next
    INDEX
    Explanations

    high-pitched sounds like squeaks, shrieks, or screams

    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
     you
    -2.14
    可能な
    -1.82
     endure
    -1.81
     also
    -1.77
     improve
    -1.77
    涙
    -1.73
     (‘
    -1.73
    ⸂
    -1.73
     miſ
    -1.72
     candidatura
    -1.71
    POSITIVE LOGITS
    </i>
    2.22
    模样
    2.00
     waarschijnlijk
    1.69
    厉害
    1.69
     "
    1.69
    噠
    1.64
     verdieping
    1.64
    驁
    1.63
     liebt
    1.63
    鸝
    1.61
    Activations Density 0.008%

    No Known Activations