© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 128935
    Prev
    Next
    INDEX
    Explanations

    make sure, readers with instructions

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

    Blockbusters, candidate, members, currencies, gear, skin, challenges

    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
    मध्ये
    0.55
    当時の
    0.51
    脛
    0.51
    削減
    0.50
    けど
    0.49
    این
    0.48
    ங்கிணை
    0.48
    㝢
    0.47
    এটা
    0.46
    Diese
    0.46
    POSITIVE LOGITS
    al
    0.46
     {
    0.45
    瑟
    0.44
    adar
    0.43
    oy
    0.42
     multit
    0.42
     k
    0.41
     Archers
    0.41
     multipart
    0.41
    xt
    0.41
    Activations Density 0.001%

    No Known Activations