© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    causes or provides results

    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
    🛐
    -0.94
    日まで
    -0.92
    巔
    -0.90
    因为它
    -0.89
    将其
    -0.88
     officielles
    -0.88
     Often
    -0.85
    ícula
    -0.85
    日を
    -0.85
    ⽽
    -0.85
    POSITIVE LOGITS
     more
    1.65
     a
    1.51
     tremendous
    1.47
     rich
    1.40
     sufficient
    1.38
     abundant
    1.34
     certain
    1.33
     corresponding
    1.31
     richer
    1.27
     enough
    1.27
    Activations Density 0.052%

    No Known Activations