© 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. 169673
    Prev
    Next
    INDEX
    Explanations

    foreign sequences

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

    plan, integrated, opportunity, managing

    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
    ნ
    0.54
     indispensables
    0.53
     xWidth
    0.50
     PROGRAM
    0.49
    Ź
    0.48
    𝙾
    0.47
     رياضيات
    0.47
    ლ
    0.46
    াউন্ড
    0.46
    ্ু
    0.45
    POSITIVE LOGITS
    alley
    0.48
    ရော
    0.48
    alien
    0.47
     fer
    0.47
    fe
    0.46
    attu
    0.46
     franch
    0.45
     managing
    0.45
    elola
    0.45
    heta
    0.45
    Activations Density 0.000%

    No Known Activations