© 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. 74849
    Prev
    Next
    INDEX
    Explanations

    physical processes and measures

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

    insurance options, installation, feedback, questions

    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
     এন্ড
    0.43
    srt
    0.41
    hti
    0.41
    ood
    0.39
    Outlet
    0.39
     الرابع
    0.39
     and
    0.39
    ̻
    0.38
    uld
    0.38
    licht
    0.38
    POSITIVE LOGITS
     Referred
    0.47
    ப்படுத்த
    0.44
     इसको
    0.42
    整治
    0.42
     genomics
    0.39
     enacted
    0.39
     زیاد
    0.39
     through
    0.38
    通过
    0.38
     чрез
    0.38
    Activations Density 0.000%

    No Known Activations