© 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. 30377
    Prev
    Next
    INDEX
    Explanations

    gives reputation

    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
     parfaitement
    -0.79
     cgi
    -0.79
    همه
    -0.77
    uVar
    -0.75
    registration
    -0.73
     supplé
    -0.73
     Prun
    -0.73
    Titel
    -0.72
     ſtill
    -0.71
     Fow
    -0.69
    POSITIVE LOGITS
     unresponsive
    0.76
     berisi
    0.73
     Theory
    0.71
    praš
    0.71
     theor
    0.68
    理論
    0.66
     bomb
    0.66
     theory
    0.64
     листопада
    0.63
     into
    0.63
    Activations Density 0.047%

    No Known Activations