© 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. 128141
    Prev
    Next
    INDEX
    Explanations

    camera shouldrestaurant plates upwhether clericalevaluation isfollowing a

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

    religious contexts, Git, culinary terms

    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
     সময়ই
    0.54
     birinci
    0.48
    وري
    0.48
     desenvolved
    0.46
     لديها
    0.46
    ث
    0.45
     humbled
    0.44
    ية
    0.44
    }))$
    0.42
    لت
    0.42
    POSITIVE LOGITS
     Namespace
    0.49
    Pascal
    0.46
     Sylvain
    0.46
     Pascal
    0.45
     Banquet
    0.44
     gastronomic
    0.43
    :"",
    0.43
     Culinary
    0.43
    STTS
    0.42
    nang
    0.42
    Activations Density 0.000%

    No Known Activations