© 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. 27700
    Prev
    Next
    INDEX
    Explanations

    CPI, loop, brightest

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

    gamma function

    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
     Industry
    0.42
     this
    0.41
     collaborative
    0.41
     curated
    0.40
    ৷
    0.40
    、（
    0.39
     moderated
    0.39
    、
    0.39
     Güzel
    0.38
     ক্রমশ
    0.38
    POSITIVE LOGITS
     प्रीवियस
    0.37
    连忙
    0.37
     दसवीं
    0.37
    주일
    0.37
     مربوط
    0.37
     vliegt
    0.36
     duże
    0.35
     hitt
    0.35
    manha
    0.35
    去找
    0.35
    Activations Density 0.000%

    No Known Activations