© 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. 175146
    Prev
    Next
    INDEX
    Explanations

    brand names

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

    Aurelius, trolley

    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
    игра
    0.56
    detection
    0.54
    自動車
    0.53
    ሖ
    0.50
     سی
    0.50
    δη
    0.50
    دی
    0.49
    ﺪ
    0.48
     synthes
    0.48
    FUNCTION
    0.48
    POSITIVE LOGITS
     Pani
    0.49
     masu
    0.46
     granted
    0.45
    },(
    0.44
    }$}
    0.44
    hii
    0.43
     ربنا
    0.43
    ቿ
    0.42
    !
    0.42
    Mas
    0.42
    Activations Density 0.000%

    No Known Activations