© 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. 212839
    Prev
    Next
    INDEX
    Explanations

    still alive

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

    examples of concepts

    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
     ஜன
    0.53
    ją
    0.51
    ędzy
    0.49
    genus
    0.48
     هنگام
    0.47
     شیخ
    0.47
    ی
    0.47
    foe
    0.47
    fak
    0.46
    constraint
    0.46
    POSITIVE LOGITS
    수
    0.58
    是
    0.48
    숨
    0.47
    싹
    0.46
    把
    0.45
    퇴
    0.45
    텔
    0.45
    這個
    0.44
    বিত্র
    0.43
    торин
    0.43
    Activations Density 0.001%

    No Known Activations