© 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. 212219
    Prev
    Next
    INDEX
    Explanations

    religious and spiritual language

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

    tokens following 'in'

    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
    c
    0.68
    ut
    0.49
    BRO
    0.47
     chiếu
    0.46
    b
    0.46
    os
    0.45
    UR
    0.45
     destac
    0.44
     personali
    0.44
    EN
    0.43
    POSITIVE LOGITS
     Nutrient
    0.47
     Conductivity
    0.44
     Veget
    0.43
     scaffolds
    0.43
     Drying
    0.43
     diuretics
    0.43
     Matches
    0.43
     Sito
    0.43
    汩
    0.43
     Logging
    0.42
    Activations Density 0.002%

    No Known Activations