© 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. 222914
    Prev
    Next
    INDEX
    Explanations

    published or greatest

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

    popular depictions, text files, output types

    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
    کول
    0.52
     hadrons
    0.51
     bienes
    0.51
    imgs
    0.49
    ൻ
    0.49
    ਵਾ
    0.48
    ರ
    0.47
     shocks
    0.47
    মঙ্গল
    0.46
    בול
    0.46
    POSITIVE LOGITS
     együtt
    0.46
    alist
    0.44
     セミ
    0.43
    t
    0.43
    ரான
    0.43
     进行
    0.42
     ฝึก
    0.41
     Krause
    0.41
     Уи
    0.41
    dh
    0.41
    Activations Density 0.000%

    No Known Activations