© 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. 31-GEMMASCOPE-2-RES-262K
    7. 41210
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    `:` or `"` followed by code/data

    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
     tattoos
    0.45
     streaks
    0.45
    Driving
    0.42
    ــ
    0.41
    Visitors
    0.41
    %!
    0.41
    ــــ
    0.41
     Tattoo
    0.41
    TOUR
    0.40
    Tour
    0.40
    POSITIVE LOGITS
    })
    0.50
    дентификаторы
    0.46
     maxn
    0.45
    หรับ
    0.43
     NONINFRINGEMENT
    0.43
    });
    0.43
     Bxa
    0.43
     SimSun
    0.42
     preprint
    0.42
     LCCN
    0.42
    Activations Density 0.892%

    No Known Activations