© 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. 31-GEMMASCOPE-2-RES-65K
    7. 55463
    Prev
    Next
    INDEX
    Explanations

    linked list definition

    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_31_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
     اللہ
    0.44
     بیماری
    0.42
    การณ์
    0.41
    疑问
    0.40
    鹏
    0.39
     conduire
    0.39
     enfermos
    0.39
    忏
    0.39
     څرنګ
    0.38
    诟
    0.38
    POSITIVE LOGITS
    val
    0.43
    ATO
    0.41
    #
    0.41
    data
    0.41
    It
    0.41
    section
    0.41
    select
    0.40
    Data
    0.40
    тук
    0.40
    cast
    0.40
    Activations Density 0.001%

    No Known Activations