© 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. 99940
    Prev
    Next
    INDEX
    Explanations

    whole followed by a noun or phrase

    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
    this
    -1.65
     This
    -1.55
     everyone
    -1.51
     only
    -1.49
    when
    -1.47
     our
    -1.45
    When
    -1.43
     lorsqu
    -1.41
     dieses
    -1.39
    What
    -1.38
    POSITIVE LOGITS
    ?”
    1.77
    cinoma
    1.59
    iligung
    1.47
     ‘
    1.45
     “
    1.44
    giarism
    1.41
     –
    1.39
    }")]
    1.38
     ‘‘
    1.37
    henswürdigkeiten
    1.33
    Activations Density 0.025%

    No Known Activations