© 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. 2690
    Prev
    Next
    INDEX
    Explanations

    amount/part of

    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
     an
    1.16
     to
    1.13
     a
    1.01
    ;
    0.92
    して
    0.83
    ید
    0.82
     в
    0.82
    ۔
    0.81
    kt
    0.80
    0
    0.80
    POSITIVE LOGITS
     of
    1.20
    يها
    1.11
    en
    1.08
    at
    1.02
    లో
    1.02
    తో
    1.02
    នៃ
    1.00
    ின்
    0.99
    tól
    0.97
    OfString
    0.97
    Activations Density 0.514%

    No Known Activations