© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 30888
    Prev
    Next
    INDEX
    Explanations

    basic / fundamental concepts

    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_40_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
     заявление
    0.44
    ósito
    0.40
     помещения
    0.39
     confrontations
    0.39
    [^
    0.38
     enjoyed
    0.38
     Conflict
    0.37
     roomy
    0.37
     Conflicts
    0.37
    னியா
    0.37
    POSITIVE LOGITS
    Basic
    0.42
     basic
    0.42
     Basic
    0.39
    basic
    0.37
    的基础
    0.37
     Biochemistry
    0.37
     βασ
    0.36
    Ṭ
    0.36
     biochemistry
    0.36
     அடிப்படை
    0.35
    Activations Density 0.000%

    No Known Activations