© 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. 150593
    Prev
    Next
    INDEX
    Explanations

    visibility, custom color, measurement mark

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

    Indigenous peoples, mentions, describing, elevates

    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
    ’
    0.50
    دين
    0.49
     COO
    0.48
     SO
    0.47
    推出
    0.46
     источ
    0.44
     burdens
    0.44
    推出的
    0.44
    "]["
    0.43
    ":
    0.43
    POSITIVE LOGITS
    adá
    0.52
     fontweight
    0.51
    también
    0.51
    ımı
    0.50
    рует
    0.50
     resistenza
    0.49
    ще
    0.49
    য়া
    0.49
    มนเชสเตอร์
    0.48
    idegg
    0.48
    Activations Density 0.000%

    No Known Activations