© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69372
    Prev
    Next
    INDEX
    Explanations

    attention to input parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     edition
    1.61
     unsh
    1.46
    散
    1.39
     localities
    1.39
     area
    1.39
     implic
    1.38
     uncont
    1.37
     exceeding
    1.37
     aircraft
    1.37
     anniversary
    1.36
    POSITIVE LOGITS
     dikkat
    1.48
    ('');
    1.35
     selecionar
    1.32
    amiseks
    1.28
    enek
    1.27
    이렇게
    1.27
    hind
    1.22
     controla
    1.22
    ระหว่าง
    1.22
     mycket
    1.19
    Activations Density 0.000%

    No Known Activations