© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8032
    Prev
    Next
    INDEX
    Explanations

    M1 motorway

    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_31_width_16k_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
    Ꮘ
    0.46
    ých
    0.40
     on
    0.39
    ović
    0.39
    राधना
    0.39
     an
    0.39
     '/'
    0.39
    ίου
    0.38
     paradig
    0.38
    ací
    0.38
    POSITIVE LOGITS
    り
    0.51
    ₃
    0.50
    ₅
    0.49
    ನನ್ನು
    0.47
    お
    0.47
    ку
    0.46
    萱
    0.46
    factory
    0.46
    на
    0.45
    ста
    0.45
    Activations Density 0.355%

    No Known Activations