© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88060
    Prev
    Next
    INDEX
    Explanations

    explaining how to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    )。
    0.57
    )，
    0.55
    ;
    0.51
    erà
    0.50
    ).
    0.49
     halides
    0.48
     divisional
    0.48
     honti
    0.47
    ล
    0.47
    erat
    0.47
    POSITIVE LOGITS
    microsoft
    0.64
    티
    0.59
     Chất
    0.59
    nt
    0.59
    larını
    0.58
     opção
    0.58
     வளர்ச்ச
    0.57
    dut
    0.55
    friction
    0.55
    тың
    0.55
    Activations Density 0.051%

    No Known Activations