© 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. 201311
    Prev
    Next
    INDEX
    Explanations

    requirements, potential, quick

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

    guaranteeing or strongly suggesting

    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
     mask
    0.46
     м
    0.45
     females
    0.45
     кг
    0.45
     П
    0.44
     masks
    0.44
    ส่
    0.44
     Д
    0.44
     MEETING
    0.43
     в
    0.43
    POSITIVE LOGITS
    instagood
    0.49
     Tapat
    0.46
    ಬಹುದು
    0.45
    fühl
    0.44
    िस्थित
    0.44
    adrenaline
    0.44
    Interfaz
    0.43
    یب
    0.43
    robespierre
    0.43
    ದುಕ
    0.43
    Activations Density 0.001%

    No Known Activations