© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65623
    Prev
    Next
    INDEX
    Explanations

    according to or about

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

    scenarios, options, or lists

    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
    ام
    0.55
    ρχ
    0.49
     particulars
    0.47
    ﻨ
    0.46
    ﻭ
    0.46
     confus
    0.46
    ﻜ
    0.46
    ك
    0.45
    〃
    0.45
    ка
    0.44
    POSITIVE LOGITS
     แบ่ง
    0.52
    bleeds
    0.51
    isku
    0.51
    orang
    0.48
    oram
    0.48
    orc
    0.47
    oron
    0.47
     bertahan
    0.47
    avamo
    0.47
     Ngf
    0.47
    Activations Density 0.000%

    No Known Activations