© 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. 65063
    Prev
    Next
    INDEX
    Explanations

    mounting ring / malnourished / student loans / these numbers / 4 days

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

    writing context

    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
     Valentines
    0.44
    पटा
    0.43
    '}).
    0.43
     ஆகியவை
    0.42
     relatório
    0.42
     বান
    0.42
    REPORT
    0.42
    ⇒
    0.42
    Valentines
    0.42
    ميل
    0.41
    POSITIVE LOGITS
    ご注意
    0.49
    ilded
    0.45
    ナ
    0.44
    otherm
    0.43
    oleum
    0.41
    ぬ
    0.41
    cripts
    0.41
    の一
    0.40
    ウォッチ
    0.40
    臨床
    0.39
    Activations Density 0.000%

    No Known Activations