© 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. 67331
    Prev
    Next
    INDEX
    Explanations

    in conference proceedings

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

    most mainstream chatbots

    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
    discussion
    0.48
     सगळ्या
    0.47
     ഇക്കാര
    0.47
     火
    0.46
     ましょう
    0.45
     కామెడీ
    0.45
    ద్రా
    0.45
    विदा
    0.45
     dicta
    0.45
    작
    0.44
    POSITIVE LOGITS
    Web
    0.42
     extrêmement
    0.40
     unsustainable
    0.38
    ুটি
    0.38
     environmentally
    0.38
     ecol
    0.38
     Websites
    0.38
     acres
    0.36
     patent
    0.36
     herm
    0.36
    Activations Density 0.000%

    No Known Activations