© 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. 145198
    Prev
    Next
    INDEX
    Explanations

    prior to or gifts

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

    http POST, waxing, algorithms, CFTR

    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
    g
    0.58
     Phật
    0.53
     なく
    0.49
     것입니다
    0.48
     বাস্তবিক
    0.48
    wu
    0.48
     স্বয়ং
    0.47
    것
    0.47
     ငါ
    0.47
     شدم
    0.46
    POSITIVE LOGITS
    romet
    0.44
     haze
    0.42
    Ante
    0.42
     Chemistry
    0.42
    Adjustment
    0.42
     proble
    0.42
    Proble
    0.42
    uraea
    0.42
     elenc
    0.41
     problematic
    0.41
    Activations Density 0.000%

    No Known Activations