© 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. 33351
    Prev
    Next
    INDEX
    Explanations

    maps and mappings

    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
    acterísticas
    0.41
    MEL
    0.38
    vening
    0.37
    enuhi
    0.36
     eternity
    0.36
     牛
    0.36
    कक्ष
    0.35
     поко
    0.35
    imismo
    0.35
    컥
    0.33
    POSITIVE LOGITS
     mapping
    1.73
    mapping
    1.58
     Mapping
    1.55
     map
    1.51
     mappings
    1.48
    映射
    1.47
    Mapping
    1.44
     Map
    1.39
    Map
    1.33
     mape
    1.32
    Activations Density 0.023%

    No Known Activations