© 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-65K
    7. 3164
    Prev
    Next
    INDEX
    Explanations

    at + noun phrase

    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_65k_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
    ة
    1.52
    ل
    1.38
    Y
    1.34
    ি
    1.30
    Z
    1.30
    ر
    1.27
    B
    1.24
    (
    1.23
    ல்
    1.18
    سة
    1.16
    POSITIVE LOGITS
    t
    2.00
    p
    1.60
    f
    1.60
    y
    1.40
    '
    1.40
     it
    1.34
    na
    1.30
    man
    1.22
    ной
    1.18
    み
    1.18
    Activations Density 0.134%

    No Known Activations