© 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. 49728
    Prev
    Next
    INDEX
    Explanations

    location identifiers

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

    funny joke, thoughtful surprise, bloody skid

    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
     яго
    0.53
     sí
    0.52
    اية
    0.49
    ᄉ
    0.46
     sitios
    0.46
     Gigabit
    0.46
     зато
    0.45
     greatness
    0.45
    ENTS
    0.44
     toot
    0.44
    POSITIVE LOGITS
    찬가지
    0.47
    genheim
    0.44
     জাহাঙ্গীর
    0.44
    宣
    0.43
    ৈত
    0.42
     demuestra
    0.42
     deoarece
    0.42
     nonostante
    0.42
     Determines
    0.42
    રોના
    0.42
    Activations Density 0.000%

    No Known Activations