© 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. 80420
    Prev
    Next
    INDEX
    Explanations

    crystal lamps

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

    accidental success, meaningful success

    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
    ARS
    0.55
    ären
    0.49
     daba
    0.48
     mana
    0.47
     yù
    0.46
     colleague
    0.45
     仕事
    0.45
     ო
    0.44
    起的
    0.44
     pun
    0.44
    POSITIVE LOGITS
    는
    0.49
    ,"%
    0.48
     olacak
    0.46
    ק
    0.44
    ნიშვნ
    0.44
    洲
    0.44
    .'%
    0.43
    ia
    0.43
     reaches
    0.43
    ίας
    0.43
    Activations Density 0.000%

    No Known Activations