© 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. 31-GEMMASCOPE-2-RES-262K
    7. 123985
    Prev
    Next
    INDEX
    Explanations

    diameter, change, structure

    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_31_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
    scholar
    0.42
    hibited
    0.41
    াকর্ম
    0.41
    entertain
    0.41
    ከ
    0.40
    rights
    0.40
    mselves
    0.40
    announce
    0.40
    compet
    0.39
    ógico
    0.39
    POSITIVE LOGITS
     changes
    0.58
     estructura
    0.58
     estructuras
    0.57
     Veränderungen
    0.54
     rythme
    0.53
     estruturas
    0.53
     sido
    0.52
     a
    0.51
     estrutura
    0.51
     cambios
    0.50
    Activations Density 0.008%

    No Known Activations