© 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. 148006
    Prev
    Next
    INDEX
    Explanations

    Catholic Church

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

    negative states or conditions

    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
     hour
    0.54
     Hour
    0.52
    Hour
    0.51
    c
    0.51
    compute
    0.50
    Promises
    0.49
    سازی
    0.48
    m
    0.48
    ಟರ್
    0.47
    承诺
    0.47
    POSITIVE LOGITS
    량을
    0.43
     살펴보
    0.42
    에서는
    0.42
     Москвы
    0.42
     helplessly
    0.42
    出现的
    0.41
     deceptive
    0.41
    와의
    0.40
    ählt
    0.40
    khane
    0.39
    Activations Density 0.001%

    No Known Activations