© 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. 117660
    Prev
    Next
    INDEX
    Explanations

    words following measuring units

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

    Attacks, Stimulation, Yield, Triangle, Narrative

    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
    PHONE
    0.48
     Phrases
    0.47
    あなたが
    0.47
    あなたの
    0.46
    ொள்
    0.45
    Closeup
    0.44
    🍥
    0.44
    여행
    0.44
    üğünüz
    0.43
    outgoing
    0.43
    POSITIVE LOGITS
     brengen
    0.45
     harmon
    0.45
     reiv
    0.45
     reclaim
    0.44
     hava
    0.44
     használ
    0.42
     만들기
    0.42
     explotación
    0.42
     tote
    0.42
     री
    0.42
    Activations Density 0.001%

    No Known Activations