© 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. 126703
    Prev
    Next
    INDEX
    Explanations

    learning or asking why

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

    cannot change or control

    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
    ইহ
    0.53
     antennes
    0.52
    বর্তমানে
    0.48
    <unused23>
    0.47
     personnes
    0.46
     ahorita
    0.46
     গুরুতর
    0.46
    Hiện
    0.45
     toilets
    0.45
     początku
    0.44
    POSITIVE LOGITS
    rotic
    0.44
    ⏱
    0.43
    LING
    0.42
     MATCH
    0.40
    delicious
    0.39
     ஆண்டுக
    0.39
     щоб
    0.39
     decad
    0.39
     diffic
    0.38
    Origen
    0.38
    Activations Density 0.001%

    No Known Activations