© 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. 123431
    Prev
    Next
    INDEX
    Explanations

    bonus features, required content, guest post

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

    needing massive, often creates, truly classic

    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
    ك
    0.46
     writing
    0.45
    ו
    0.44
     Smiley
    0.43
     restructuring
    0.42
    affa
    0.42
     GROUP
    0.41
     Dudley
    0.41
     CARE
    0.41
    দ
    0.40
    POSITIVE LOGITS
    ्ट
    0.53
    𝑠
    0.53
    牲
    0.53
    સભા
    0.52
    ມື
    0.51
    is
    0.50
     evrops
    0.50
     इलाकों
    0.50
    푀
    0.49
    reements
    0.48
    Activations Density 0.002%

    No Known Activations