© 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. 195048
    Prev
    Next
    INDEX
    Explanations

    card, central, letters, commanding

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

    Astana, Kazakhstan

    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
    اتف
    0.44
    记得
    0.43
    ధ్య
    0.43
    לט
    0.42
    דה
    0.42
    仍然
    0.42
    в
    0.41
    如
    0.40
    ティーク
    0.40
     Wys
    0.40
    POSITIVE LOGITS
    emia
    0.51
    achal
    0.49
     ईडी
    0.48
     อุ
    0.48
     andra
    0.48
     सिर
    0.47
     Educa
    0.47
    ിച്ച
    0.47
     imprend
    0.46
    autres
    0.46
    Activations Density 0.001%

    No Known Activations