© 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. 106950
    Prev
    Next
    INDEX
    Explanations

    code constructs and types

    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
     CERTAIN
    -1.15
    átek
    -1.08
    oped
    -1.02
    [][
    -0.99
    honestly
    -0.98
     matt
    -0.94
     patienter
    -0.94
     SIMILAR
    -0.93
     PATIENT
    -0.93
    itize
    -0.92
    POSITIVE LOGITS
     final
    1.48
    final
    1.40
     long
    1.27
     from
    1.15
     even
    0.97
     finally
    0.94
    List
    0.93
    long
    0.90
    </i>
    0.89
     possibly
    0.89
    Activations Density 0.013%

    No Known Activations