© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212971
    Prev
    Next
    INDEX
    Explanations

    news sources and local updates

    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
     више
    0.38
     журнали
    0.37
    LT
    0.37
    俗
    0.36
     journalism
    0.36
    新闻
    0.36
     більше
    0.36
    候
    0.36
    образие
    0.35
     میڈیا
    0.35
    POSITIVE LOGITS
     relaxed
    0.44
     mountainous
    0.40
     marble
    0.39
     purified
    0.39
    irs
    0.39
    wey
    0.39
     tasks
    0.38
    ின்றது
    0.38
    にく
    0.38
     Wey
    0.38
    Activations Density 0.001%

    No Known Activations