© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 224728
    Prev
    Next
    INDEX
    Explanations

    level, position, height

    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
    地面
    0.47
    otus
    0.41
     ground
    0.40
     terreno
    0.40
    壃
    0.39
     richting
    0.38
    Direction
    0.38
     zemlji
    0.38
    terrain
    0.37
     pleinement
    0.36
    POSITIVE LOGITS
    高さ
    0.99
     height
    0.95
     높
    0.92
     heights
    0.91
     высота
    0.88
    Height
    0.84
    높
    0.84
     Height
    0.84
     высоте
    0.84
     altura
    0.83
    Activations Density 0.027%

    No Known Activations