© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 106873
    Prev
    Next
    INDEX
    Explanations

    napkin and its uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    0.59
    ،
    0.56
     for
    0.55
    ła
    0.54
    },
    0.54
    inta
    0.53
    este
    0.51
    irus
    0.51
    ovel
    0.51
    ante
    0.51
    POSITIVE LOGITS
     વ્યક્તિ
    0.55
    ايا
    0.54
     ሆ
    0.54
     údaje
    0.54
     بيت
    0.53
     Einwill
    0.52
    
    0.52
     ઘરે
    0.52
    Vcs
    0.52
    Ｋ
    0.52
    Activations Density 0.000%

    No Known Activations