© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 104955
    Prev
    Next
    INDEX
    Explanations

    experience equivalent

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

    functions, roles, and technical terms

    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
     事件
    0.40
    νας
    0.40
    и
    0.39
     体
    0.38
    ்சை
    0.38
     sermon
    0.38
    ustible
    0.38
    도의
    0.37
    섭
    0.37
     ток
    0.37
    POSITIVE LOGITS
     braucht
    0.46
    æss
    0.46
     komm
    0.45
     volledig
    0.45
     orden
    0.44
     bonne
    0.44
    defense
    0.44
     Під
    0.44
     ausgeführt
    0.44
     klasse
    0.44
    Activations Density 0.001%

    No Known Activations