© 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. 97166
    Prev
    Next
    INDEX
    Explanations

    Kingston for professional memory

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

    specific examples or alternatives

    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
     письма
    0.40
     разработан
    0.39
    ಐ
    0.39
    administered
    0.38
    gery
    0.38
    zé
    0.37
    áj
    0.37
     Petrol
    0.36
     założ
    0.35
    ເສ
    0.35
    POSITIVE LOGITS
     国
    0.44
     synonym
    0.42
    原子炉
    0.42
    國
    0.42
     ク
    0.41
    堇
    0.41
     to
    0.40
     pivot
    0.40
    ゲーム
    0.39
     collage
    0.38
    Activations Density 0.000%

    No Known Activations