© 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. 31524
    Prev
    Next
    INDEX
    Explanations

    file operations

    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
     your
    -1.10
    pared
    -1.04
     problèmes
    -1.00
    zaak
    -0.98
    mermaid
    -0.97
    anians
    -0.95
    Referencie
    -0.93
    ┑
    -0.93
    icycle
    -0.91
    brtc
    -0.91
    POSITIVE LOGITS
    there
    1.05
    ——”
    0.97
     during
    0.93
     while
    0.93
    after
    0.86
    uncurkan
    0.85
    viele
    0.85
     after
    0.85
    آیا
    0.85
    generic
    0.84
    Activations Density 0.009%

    No Known Activations