© 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. 226080
    Prev
    Next
    INDEX
    Explanations

    Gabbard, Democratic Primary, style icon

    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
    ة
    0.57
    </h2>
    0.56
    '
    0.56
    ı
    0.53
    á
    0.50
    agger
    0.49
    oc
    0.48
    aths
    0.46
    \",
    0.46
    ay
    0.46
    POSITIVE LOGITS
     അടി
    0.49
    ADDING
    0.47
     бясплат
    0.45
     رسول
    0.45
     మన
    0.44
     vecino
    0.44
     порядку
    0.43
     സമയ
    0.43
     მ
    0.43
     మనం
    0.43
    Activations Density 0.000%

    No Known Activations