© 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. 35082
    Prev
    Next
    INDEX
    Explanations

    io.BytesIO

    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
     E
    0.61
    ach
    0.60
     T
    0.58
     die
    0.58
     CEC
    0.58
     breach
    0.58
     O
    0.57
    ari
    0.57
    yl
    0.57
     AR
    0.57
    POSITIVE LOGITS
    고
    0.79
    رفة
    0.68
    لی
    0.67
    나
    0.66
    داء
    0.66
    스
    0.66
    された
    0.65
    دى
    0.64
    ت
    0.64
    ת
    0.64
    Activations Density 0.004%

    No Known Activations