© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 132823
    Prev
    Next
    INDEX
    Explanations

    noun phrase completion

    np_acts-logits-general · gemini-2.5-flash-lite

    awaiting completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    0.48
    ريكية
    0.47
     podmín
    0.46
     peligro
    0.46
     شرط
    0.44
     bør
    0.44
     verification
    0.44
     マル
    0.43
     kondisi
    0.43
     proposito
    0.43
    POSITIVE LOGITS
    ;<
    0.49
    ーツ
    0.47
    뇨
    0.47
     associating
    0.46
    <tfoot>
    0.45
    르게
    0.45
    າດ
    0.45
    featureType
    0.45
     нее
    0.44
    ानंतर
    0.44
    Activations Density 0.000%

    No Known Activations