© 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. 69607
    Prev
    Next
    INDEX
    Explanations

    sequences ending sentences

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

    control, manage, increase, largest, store

    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
     economical
    0.52
     mes
    0.48
    충
    0.47
     cuant
    0.47
    꼼
    0.47
     nuest
    0.46
    不好
    0.46
     نع
    0.46
    غ
    0.46
     bastard
    0.44
    POSITIVE LOGITS
    ˌ
    0.50
    šenje
    0.46
     словами
    0.46
     घटक
    0.46
     উপাদান
    0.45
    JSPA
    0.45
     замети
    0.45
    Ɔ
    0.45
    Russ
    0.44
    ింది
    0.44
    Activations Density 0.001%

    No Known Activations