© 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. 118492
    Prev
    Next
    INDEX
    Explanations

    Column followed by name or rank

    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
    s
    1.45
    d
    1.41
    ی
    1.14
    n
    1.13
    p
    1.08
    ים
    1.01
    am
    1.00
    the
    0.98
    i
    0.98
    ط
    0.95
    POSITIVE LOGITS
    ем
    0.91
     aversion
    0.81
     aliphatic
    0.78
    jší
    0.78
    ния
    0.75
    的能力
    0.73
     expériment
    0.70
     hấp
    0.70
     appréci
    0.70
    aecat
    0.67
    Activations Density 0.000%

    No Known Activations