© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3272
    Prev
    Next
    INDEX
    Explanations

    walk followed by direction

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

    walking along

    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
     wrestle
    0.39
     }_{
    0.39
     செயற்க
    0.38
    깔
    0.38
    ற்க
    0.37
     座
    0.37
    랏
    0.37
    Attempts
    0.37
    Transient
    0.37
    ្ខ
    0.36
    POSITIVE LOGITS
    🚶
    0.94
     around
    0.90
     barefoot
    0.89
    around
    0.86
     streets
    0.82
     distances
    0.82
     вокруг
    0.82
     alrededor
    0.80
     rundt
    0.79
     حول
    0.77
    Activations Density 0.193%

    No Known Activations