© 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. 78537
    Prev
    Next
    INDEX
    Explanations

    from the

    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
    a
    -1.31
     
    -1.27
     шесть
    -1.08
     "
    -1.06
     gleicher
    -1.05
     …
    -1.04
        
    -1.02
    }$.
    -1.02
     was
    -1.01
     specify
    -1.00
    POSITIVE LOGITS
     being
    1.85
     whence
    1.48
     the
    1.47
     consideration
    1.41
     beneath
    1.41
     their
    1.27
     khỏi
    1.23
    Berdasarkan
    1.20
     within
    1.19
     afar
    1.13
    Activations Density 0.055%

    No Known Activations