© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42155
    Prev
    Next
    INDEX
    Explanations

    .

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sepen
    0.29
     والله
    0.28
     он
    0.28
     его
    0.27
     を
    0.26
     το
    0.26
     인생
    0.26
     જ
    0.26
     전
    0.26
    มัน
    0.26
    POSITIVE LOGITS
    也可以
    0.32
    +\|\
    0.32
    exception
    0.31
    cada
    0.29
    வ்வாறு
    0.29
    érence
    0.29
    styled
    0.28
    kd
    0.28
    このような
    0.28
    कडील
    0.28
    Activations Density 0.053%

    No Known Activations