© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77612
    Prev
    Next
    INDEX
    Explanations

    something went wrong

    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
    ochet
    -0.72
    ziu
    -0.71
    tsu
    -0.71
     PROGRAMS
    -0.69
     úspě
    -0.67
    utkan
    -0.66
     Cellar
    -0.65
    nuc
    -0.63
     commerciales
    -0.63
    rieta
    -0.63
    POSITIVE LOGITS
    Edge
    0.72
     Rade
    0.69
    business
    0.66
    verge
    0.65
     Edge
    0.64
     Nal
    0.64
     naturen
    0.63
    lts
    0.63
    Sentence
    0.63
    ijuana
    0.63
    Activations Density 0.087%

    No Known Activations