© 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. 165413
    Prev
    Next
    INDEX
    Explanations

    support crew, managed to, Published Kingdom, emergency app

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

    list descriptions

    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
     կար
    0.54
    acionais
    0.53
     postérieur
    0.53
    endig
    0.51
    ższej
    0.51
     દિ
    0.51
     싶
    0.48
     рели
    0.47
     ලැබේ
    0.47
    lení
    0.46
    POSITIVE LOGITS
    i
    0.52
    ोटे
    0.48
     project
    0.48
    Про
    0.48
    정
    0.47
    ANG
    0.46
     country
    0.46
     patents
    0.45
    ي
    0.45
    피
    0.45
    Activations Density 0.000%

    No Known Activations