© 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. 24185
    Prev
    Next
    INDEX
    Explanations

    origins, Nutrient, fact, hope

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

    resource enforcement challenges maps transformation

    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
    ítő
    0.45
    此
    0.43
     Hilbert
    0.42
     Shortcut
    0.42
     cool
    0.40
    仪器
    0.39
     Physics
    0.39
    ‹
    0.39
     Js
    0.38
    艺术
    0.38
    POSITIVE LOGITS
     まず
    0.47
    '،
    0.47
    amati
    0.47
    ”،
    0.47
    ವಾಡ
    0.46
    "،
    0.46
    origins
    0.46
    してみました
    0.45
    َع
    0.44
    NETWORK
    0.43
    Activations Density 0.000%

    No Known Activations