© 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. 34-GEMMASCOPE-RES-131K
    7. 57275
    Prev
    Next
    INDEX
    Explanations

    giving reasons or explanations

    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_34/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
     nestled
    -1.44
    彼女は
    -1.26
     conector
    -1.24
     overtly
    -1.23
     exquisitely
    -1.23
    他现在
    -1.23
     adorno
    -1.23
     caoutchouc
    -1.20
     irrespective
    -1.20
    另一个
    -1.18
    POSITIVE LOGITS
    They
    1.83
     they
    1.63
    そのため
    1.57
     They
    1.45
     Its
    1.45
    その
    1.30
    Therefore
    1.29
     it
    1.28
    Its
    1.25
    they
    1.22
    Activations Density 0.119%

    No Known Activations