© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5345
    Prev
    Next
    INDEX
    Explanations

    downsizing, hills, stairs, below

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

    breakdown of

    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
    ขึ้น
    0.51
     najwy
    0.47
     høy
    0.47
     hoog
    0.45
     Highest
    0.45
     العليا
    0.44
    抨
    0.44
     hög
    0.43
     høj
    0.43
    最高
    0.43
    POSITIVE LOGITS
    stairs
    0.75
    hills
    0.70
     stairs
    0.65
     thấp
    0.65
    hearted
    0.65
    hill
    0.64
    ↓↓
    0.61
    ⬇
    0.60
     below
    0.59
    sizing
    0.58
    Activations Density 0.067%

    No Known Activations