© 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. 198127
    Prev
    Next
    INDEX
    Explanations

    parts and romance was

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

    operating systems, dust, cGMP, evaluate, OCR

    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
     خدمت
    0.44
    प्ता
    0.44
    㛺
    0.42
     Passenger
    0.41
    َي
    0.40
     aliments
    0.40
    ِه
    0.40
    َهُ
    0.40
    莨
    0.39
     Parser
    0.38
    POSITIVE LOGITS
    タリア
    0.50
    nikiem
    0.50
    пози
    0.50
    at
    0.49
     აქვს
    0.48
    fier
    0.48
     kiezen
    0.46
    tetra
    0.46
    tet
    0.46
     conferencia
    0.46
    Activations Density 0.001%

    No Known Activations