© 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. 77993
    Prev
    Next
    INDEX
    Explanations

    reporting from a source

    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
    ciaż
    -0.98
     tdci
    -0.92
     dirit
    -0.88
    EDR
    -0.88
    sera
    -0.88
     INE
    -0.88
    時間
    -0.87
    GALLERY
    -0.86
    </tr>
    -0.85
     tirs
    -0.84
    POSITIVE LOGITS
     a
    2.08
     an
    1.60
     response
    1.44
     einem
    1.31
     describing
    1.26
    ponse
    1.23
     reply
    1.20
     explaining
    1.16
     passing
    1.16
     jest
    1.16
    Activations Density 0.056%

    No Known Activations