© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 16820
    Prev
    Next
    INDEX
    Explanations

    Commodore International, Nationwide

    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
     in
    0.59
    v
    0.50
     canto
    0.47
    ร
    0.46
     on
    0.46
    owering
    0.46
     actresses
    0.42
     inciting
    0.42
     odio
    0.41
    ્ટ
    0.41
    POSITIVE LOGITS
    ので
    0.54
    보니
    0.51
    ه
    0.51
    мышлен
    0.51
    ප්
    0.51
     специали
    0.50
    할
    0.50
    보면
    0.50
     Médico
    0.50
    പേ
    0.49
    Activations Density 0.007%

    No Known Activations