© 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. 107110
    Prev
    Next
    INDEX
    Explanations

    width, height, size

    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
    やはり
    -1.00
     dAtA
    -0.96
     }{@
    -0.92
    hrter
    -0.92
     شنبه
    -0.90
    analisi
    -0.89
     Energia
    -0.88
    }</
    -0.88
     called
    -0.88
    態度
    -0.87
    POSITIVE LOGITS
    0
    1.34
     decenas
    1.02
     then
    0.91
     anfangen
    0.91
    μένος
    0.90
    紝
    0.89
    rokken
    0.87
     longtime
    0.84
     Материал
    0.84
     gainera
    0.84
    Activations Density 0.018%

    No Known Activations