© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 194722
    Prev
    Next
    INDEX
    Explanations

    technical process descriptors

    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_40_width_262k_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
     indicador
    0.44
     señal
    0.43
    Voc
    0.42
     habilidades
    0.41
     Campe
    0.40
     parum
    0.40
    纜
    0.40
     scholars
    0.40
     Spoon
    0.40
    ப்படவில்லை
    0.40
    POSITIVE LOGITS
    ญิง
    0.41
    akum
    0.39
     вспомина
    0.38
    MNumber
    0.38
    :\/\/
    0.38
     بقى
    0.37
     bây
    0.37
     worksheet
    0.36
     sublicense
    0.36
    aughan
    0.36
    Activations Density 0.000%

    No Known Activations