© 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. 2154
    Prev
    Next
    INDEX
    Explanations

    Reform, tarif, announce, bold, fluid

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

    questions about entities and actions

    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
     Houston
    0.59
     H
    0.57
     U
    0.53
     D
    0.51
     Hu
    0.51
    </code>
    0.50
     Durante
    0.50
     Box
    0.49
    ä
    0.49
    āla
    0.49
    POSITIVE LOGITS
    Reform
    0.52
    Kale
    0.51
    Atlant
    0.50
    鹹
    0.50
    tarif
    0.49
    Astr
    0.48
    ⵕ
    0.48
    Akh
    0.47
    lectoral
    0.47
    reform
    0.46
    Activations Density 0.000%

    No Known Activations