© 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. 54890
    Prev
    Next
    INDEX
    Explanations

    plans or location

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

    focus on other speakers

    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
     but
    0.46
     underscore
    0.44
    신기
    0.44
     taxonomic
    0.43
    龛
    0.43
     underline
    0.42
     décor
    0.41
     hooded
    0.41
     içerisinde
    0.41
    ansı
    0.40
    POSITIVE LOGITS
    llen
    0.49
     moneys
    0.45
    sentences
    0.45
     കയ
    0.42
     defList
    0.42
    交易所
    0.42
    fund
    0.42
    みんな
    0.41
    漲
    0.41
     finanzi
    0.41
    Activations Density 0.000%

    No Known Activations