© 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. 66003
    Prev
    Next
    INDEX
    Explanations

    verses, daughters

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

    Functions, loops, control, 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
    Model
    0.45
    Career
    0.43
    長期
    0.42
    弱
    0.42
    stru
    0.41
     Ruch
    0.41
    Pre
    0.41
    Japanese
    0.41
     అమ
    0.40
    羅
    0.40
    POSITIVE LOGITS
    номет
    0.50
     snacks
    0.49
    шего
    0.48
     eateries
    0.46
     gehören
    0.44
    }):=\
    0.44
     канализа
    0.43
     snack
    0.42
     jurisdict
    0.42
     homic
    0.42
    Activations Density 0.001%

    No Known Activations