© 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. 201597
    Prev
    Next
    INDEX
    Explanations

    God, child, church

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

    languages and specific entities

    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
    v
    0.64
    t
    0.56
    i
    0.54
    u
    0.54
    e
    0.53
    alt
    0.52
    such
    0.52
    lo
    0.50
    l
    0.49
    r
    0.49
    POSITIVE LOGITS
     profondeur
    0.58
    睄
    0.55
     assuntos
    0.52
     blasp
    0.51
     uczni
    0.51
    GTUIKit
    0.51
     synagogue
    0.50
     Gebiet
    0.50
     scrittura
    0.50
     congregations
    0.50
    Activations Density 0.000%

    No Known Activations