© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3914
    Prev
    Next
    INDEX
    Explanations

    upward and rise

    np_acts-logits-general · gemini-2.5-flash-lite

    upward or ascending direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    烔
    0.41
     खल
    0.40
    ρέ
    0.37
    ໝ
    0.36
    ernel
    0.36
    trashItem
    0.35
    ESH
    0.34
    ಡು
    0.34
    結
    0.34
    狈
    0.34
    POSITIVE LOGITS
     upward
    3.44
     upwards
    2.94
     ascending
    2.88
     ascend
    2.84
     вверх
    2.80
     ascends
    2.80
     ascended
    2.73
    向上
    2.69
     ascent
    2.67
    上升
    2.67
    Activations Density 0.201%

    No Known Activations