© 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. 39536
    Prev
    Next
    INDEX
    Explanations

    Argentine national

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

    medical conditions or descriptions

    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
    illustration
    0.44
     Gaga
    0.43
     가지
    0.43
    impression
    0.41
    landmarks
    0.41
    `]
    0.40
     banal
    0.40
    贈り物
    0.40
    ’
    0.39
    ])
    0.38
    POSITIVE LOGITS
    Datos
    0.53
    Tổng
    0.49
    ్రో
    0.49
     النش
    0.48
    Orden
    0.48
     prioritizing
    0.47
     Frente
    0.45
     Información
    0.45
    ientras
    0.45
     Tổng
    0.45
    Activations Density 0.000%

    No Known Activations