© 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. 212283
    Prev
    Next
    INDEX
    Explanations

    describes computational methods and results

    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
    ικοί
    0.40
    ِل
    0.39
     hükü
    0.38
    政府
    0.38
     scuole
    0.38
     INDUST
    0.38
    മൂ
    0.37
    堭
    0.37
     są
    0.37
     Coupling
    0.37
    POSITIVE LOGITS
    मुख
    0.41
    although
    0.41
     realize
    0.41
     although
    0.40
    Gregory
    0.40
    恸
    0.39
     सांस
    0.38
    MORPH
    0.38
     brisk
    0.37
    ાર્થ
    0.37
    Activations Density 0.001%

    No Known Activations