© 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. 63159
    Prev
    Next
    INDEX
    Explanations

    no way to

    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
    ऱ
    -0.93
     trebui
    -0.92
    нены
    -0.90
    Quais
    -0.90
    itación
    -0.88
    zit
    -0.87
     réfugiés
    -0.87
     幅
    -0.87
     Werkstatt
    -0.86
    punkten
    -0.84
    POSITIVE LOGITS
     to
    2.66
     around
    1.98
     that
    1.70
     you
    1.61
     we
    1.47
    Around
    1.30
     out
    1.18
     they
    1.16
     forward
    1.14
     into
    1.08
    Activations Density 0.044%

    No Known Activations