© 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. 2996
    Prev
    Next
    INDEX
    Explanations

    generating reports

    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
    ла
    1.70
    ка
    1.62
    ك
    1.41
    т
    1.37
    ку
    1.22
    לים
    1.19
    з
    1.18
    на
    1.16
    ா
    1.08
    ت
    1.07
    POSITIVE LOGITS
    B
    1.25
    n
    1.16
    W
    1.15
    h
    1.12
    D
    1.10
    r
    1.09
    c
    1.09
    T
    1.06
    F
    1.02
    G
    0.99
    Activations Density 0.209%

    No Known Activations