© 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. 102479
    Prev
    Next
    INDEX
    Explanations

    foreign language content

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

    biological facts and traits

    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
    襄
    0.44
    वार
    0.42
    も
    0.42
    天天
    0.39
    aminar
    0.39
    ،
    0.39
    乖
    0.38
    応
    0.38
    每天
    0.38
    が変わ
    0.38
    POSITIVE LOGITS
     austri
    0.51
     使っ
    0.49
     주제
    0.48
    aitu
    0.47
     Gosudarstvennyj
    0.47
    glicherweise
    0.47
     ブル
    0.47
     ব্রহ্ম
    0.46
    rup
    0.46
     গিরিশ
    0.46
    Activations Density 0.001%

    No Known Activations