© 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. 10-GEMMASCOPE-RES-131K
    7. 45259
    Prev
    Next
    INDEX
    Explanations

    veteran affairs or vascular access

    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_10/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
     Then
    -3.72
     That
    -2.83
     Some
    -2.56
     Certainly
    -2.42
     algunos
    -2.41
     However
    -2.38
     übri
    -2.38
     Wonderful
    -2.36
    </em>
    -2.33
     selben
    -2.33
    POSITIVE LOGITS
    酲
    2.66
    thirds
    2.33
    fielder
    2.31
    this
    2.28
    殂
    2.19
    魴
    2.17
    ";
    2.16
    ERS
    2.13
    s
    2.13
    "
    2.09
    Activations Density 0.005%

    No Known Activations