© 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. 87700
    Prev
    Next
    INDEX
    Explanations

    tickets, member, playlists, morning, visitors

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

    goals and objectives

    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
     half
    0.46
    н
    0.46
    -
    0.43
    present
    0.43
    ührung
    0.41
     be
    0.41
    lem
    0.41
     Half
    0.41
    ž
    0.41
    prs
    0.40
    POSITIVE LOGITS
    ﻘ
    0.54
     साउथ
    0.53
    垚
    0.51
     dobbiamo
    0.50
    )});
    0.50
    鴳
    0.50
     PROJECTS
    0.50
    जनबी
    0.49
    ﻌ
    0.48
    િત
    0.47
    Activations Density 0.002%

    No Known Activations