© 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. 166345
    Prev
    Next
    INDEX
    Explanations

    school, conditions, or life related to

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

    technical and retail 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
     It
    0.50
    াব্য
    0.50
    τ
    0.49
    Jak
    0.46
    Truly
    0.46
    Empty
    0.43
     ausgel
    0.43
    apest
    0.43
    h
    0.43
    Dragged
    0.42
    POSITIVE LOGITS
     entitle
    0.50
     mili
    0.45
     entitles
    0.45
     campus
    0.44
     convierten
    0.44
    ະພັນ
    0.43
     предприя
    0.43
    ellidos
    0.43
    backslash
    0.43
     life
    0.43
    Activations Density 0.000%

    No Known Activations