© 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. 242644
    Prev
    Next
    INDEX
    Explanations

    delivered along, entry component, purposes of

    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
    -*
    0.51
     افز
    0.49
     امریک
    0.48
    -]
    0.47
     單
    0.46
     কোথাও
    0.46
    -{
    0.46
     תק
    0.46
     ance
    0.46
    \*
    0.45
    POSITIVE LOGITS
    딛
    0.44
     poses
    0.44
    （
    0.42
    chodu
    0.41
     Fitch
    0.41
    готов
    0.41
     Liga
    0.40
    ాతీయ
    0.40
     Goff
    0.40
    蛔
    0.40
    Activations Density 0.001%

    No Known Activations