© 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. 15136
    Prev
    Next
    INDEX
    Explanations

    treatment, support, software, color

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

    unique math quizzes

    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
     முன்பு
    0.40
    𝘞
    0.38
     ይችላሉ
    0.37
    荩
    0.37
    잤
    0.36
    黜
    0.36
    荪
    0.36
     معناها
    0.36
     কণ্
    0.35
    層
    0.35
    POSITIVE LOGITS
    (!)
    0.53
     (!)
    0.50
    且
    0.42
    ophon
    0.38
     multimillion
    0.38
     hochwertige
    0.36
     غیر
    0.36
     multipurpose
    0.36
    jan
    0.35
    zing
    0.35
    Activations Density 0.165%

    No Known Activations