© 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. 180687
    Prev
    Next
    INDEX
    Explanations

    ways to interact

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

    perfectionistic, dance, directly, square root

    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
     Considering
    0.49
     Until
    0.49
     Shun
    0.48
    yny
    0.48
     Subsequently
    0.44
     Honestly
    0.44
     Vs
    0.44
    잖
    0.44
     Hmm
    0.44
     Babu
    0.43
    POSITIVE LOGITS
    咶
    0.53
    inä
    0.48
    وینت
    0.47
     का
    0.46
    Pall
    0.45
     کور
    0.45
    Apache
    0.44
    舏
    0.44
     골
    0.44
    㽞
    0.43
    Activations Density 0.000%

    No Known Activations