© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 54452
    Prev
    Next
    INDEX
    Explanations

    exit sub or error handler

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

    closing delimiters or semicolons

    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_31_width_262k_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
    OLYBD
    0.43
     Straßen
    0.40
    otan
    0.39
    }$;
    0.39
    ubu
    0.38
     petitioned
    0.38
    u
    0.38
    ys
    0.37
     उभ
    0.37
    .;
    0.37
    POSITIVE LOGITS
     なお
    0.42
    +')
    0.41
     hợp
    0.40
    
    0.40
    ทั้งหมด
    0.40
    もちろん
    0.39
    +'
    0.38
     доме
    0.38
     Пер
    0.38
     앞에
    0.38
    Activations Density 0.000%

    No Known Activations