© 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. 30696
    Prev
    Next
    INDEX
    Explanations

    African Sun

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

    consequences, expectations, reactions, fantasy, observation

    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
    愔
    0.46
    纡
    0.43
    хоро
    0.41
    拎
    0.41
     К
    0.41
    there
    0.41
    もある
    0.41
     QUAD
    0.41
    慝
    0.41
     शीघ्र
    0.40
    POSITIVE LOGITS
    httpRequest
    0.46
     unresponsive
    0.45
    حيان
    0.45
    大規模
    0.45
     عملکرد
    0.45
    hydroxyl
    0.43
    HttpResponse
    0.42
    بيب
    0.42
    ული
    0.42
    funcion
    0.40
    Activations Density 0.001%

    No Known Activations