© 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. 97418
    Prev
    Next
    INDEX
    Explanations

    purchased elsewhere

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

    limited resources, non-english awards

    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
    :
    0.43
    (
    0.42
     அழி
    0.40
    SAVE
    0.39
     consumir
    0.39
     triglyceride
    0.38
     can
    0.38
     planetary
    0.38
     climatic
    0.37
    cyan
    0.37
    POSITIVE LOGITS
    袠
    0.47
     décerné
    0.47
     рассказыва
    0.46
    medallas
    0.45
    两个人
    0.44
    军队
    0.44
    ęs
    0.43
    顾问
    0.43
    ayutt
    0.43
     najwy
    0.43
    Activations Density 0.001%

    No Known Activations