© 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. 222023
    Prev
    Next
    INDEX
    Explanations

    straight away

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

    JavaScript, projects, definitive versions

    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
     four
    0.49
     ਇੱਕ
    0.47
    3
    0.46
     behem
    0.46
     ಒಂದು
    0.44
    CAN
    0.43
     bombardment
    0.43
    MUST
    0.43
    2
    0.43
    ιε
    0.43
    POSITIVE LOGITS
     участ
    0.54
    veriş
    0.49
     стоимость
    0.49
     ব্যবসায়
    0.49
     ギフト
    0.48
    खाव
    0.47
     시간이
    0.46
    婚礼
    0.45
     উপকৃত
    0.45
     مراسم
    0.44
    Activations Density 0.000%

    No Known Activations