© 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. 16-GEMMASCOPE-2-RES-262K
    7. 118750
    Prev
    Next
    INDEX
    Explanations

    parallax animations

    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_16_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
    ொள்
    0.58
     baff
    0.57
    क्रोश
    0.54
     Kusum
    0.53
    ᖕ
    0.50
     canisters
    0.50
    on
    0.49
    க்கொள்
    0.49
     carénés
    0.48
    䬲
    0.48
    POSITIVE LOGITS
    0
    0.57
    2
    0.53
     Aleg
    0.48
    개가
    0.46
    ຕ້ອງການ
    0.46
    বর্ত
    0.46
    țe
    0.45
     খাওয়া
    0.45
    ড়া
    0.44
    (
    0.44
    Activations Density 0.000%

    No Known Activations