© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 2015
    Prev
    Next
    INDEX
    Explanations

    the [concept/entity]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     في
    1.89
     на
    1.82
     в
    1.72
     من
    1.69
     и
    1.62
     in
    1.61
    .
    1.61
     ل
    1.57
     to
    1.48
     لل
    1.48
    POSITIVE LOGITS
    טאטורק
    1.19
    SourceFinding
    1.17
    ConfigureArg
    1.16
    AutorLabel
    1.16
    PastPositions
    1.14
    𒊨
    1.12
    btnEjercicio
    1.12
    scpService
    1.12
    ꗜ
    1.11
    smallestBlock
    1.11
    Activations Density 0.000%

    No Known Activations