© 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. 33566
    Prev
    Next
    INDEX
    Explanations

    successful homeJuly datehelp drive outbrotherbest Pan-Africansilent loss

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

    isolated power, higher altitude, silence, currencies, diagrams

    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
    볼
    0.47
     jie
    0.47
     hinzuf
    0.47
     wyposaż
    0.45
     zhōng
    0.44
    火车
    0.44
     男女
    0.44
    育
    0.44
    积分
    0.43
    ǎi
    0.43
    POSITIVE LOGITS
    abdominal
    0.49
    یم
    0.42
    無需
    0.42
    IM
    0.41
     novas
    0.41
    जेश
    0.41
    {
    0.40
    в
    0.40
    cendo
    0.39
     selles
    0.39
    Activations Density 0.000%

    No Known Activations