© 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. 29516
    Prev
    Next
    INDEX
    Explanations

    kn words and their common endings

    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
    is
    2.09
    t
    1.84
    v
    1.79
    c
    1.78
    f
    1.67
    j
    1.59
    g
    1.53
    z
    1.49
    n
    1.45
    to
    1.40
    POSITIVE LOGITS
    و
    1.25
    ление
    1.19
    з
    1.18
    کن
    1.17
     discredited
    1.12
    ם
    1.12
    ו
    1.11
    す
    1.09
    ל
    1.09
    که
    1.08
    Activations Density 0.009%

    No Known Activations