© 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. 220103
    Prev
    Next
    INDEX
    Explanations

    time to reveal or discovery

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

    colorful splashes or paint

    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
    掮
    0.47
    Ту
    0.44
    Фи
    0.43
    П
    0.43
    Нор
    0.43
    Ц
    0.42
    Ю
    0.42
    З
    0.42
    钕
    0.42
    Mannschaft
    0.42
    POSITIVE LOGITS
     d
    0.55
     was
    0.55
     hight
    0.51
     humbled
    0.50
    d
    0.50
     mantenimiento
    0.50
     elkaar
    0.50
     enero
    0.50
     cig
    0.49
     deber
    0.49
    Activations Density 0.001%

    No Known Activations