© 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. 172518
    Prev
    Next
    INDEX
    Explanations

    Nice feelings or positive moments

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

    God, sqlite, access

    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
    -
    0.57
    z
    0.55
    oda
    0.52
    n
    0.50
    i
    0.49
    tab
    0.49
    uing
    0.48
    r
    0.48
    race
    0.47
    er
    0.47
    POSITIVE LOGITS
     фармацев
    0.55
    劫
    0.54
     말씀
    0.49
     DMBT
    0.48
    তামূলক
    0.48
     Maarten
    0.47
     CCOC
    0.47
     患者
    0.47
    瘙
    0.47
     संभावनाएं
    0.46
    Activations Density 0.000%

    No Known Activations