© 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. 89246
    Prev
    Next
    INDEX
    Explanations

    cmake build system

    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
    uje
    0.76
    การ
    0.74
    owaniu
    0.68
    ید
    0.68
     a
    0.66
    ang
    0.65
    ania
    0.64
    inan
    0.63
    ě
    0.62
    ۰
    0.61
    POSITIVE LOGITS
    ي
    0.60
     têm
    0.59
    dice
    0.57
    cer
    0.56
     iris
    0.56
     ultimo
    0.56
     éclair
    0.56
    ciamo
    0.55
    ziehen
    0.55
     erzählt
    0.55
    Activations Density 0.001%

    No Known Activations