© 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. 105988
    Prev
    Next
    INDEX
    Explanations

    time duration and quantity

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

    Satan and opposing God

    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
    मग
    0.46
    decl
    0.43
     我们
    0.43
    classname
    0.43
    阍
    0.41
    ält
    0.40
    メラ
    0.40
    뿡
    0.40
     మూ
    0.40
    ▐
    0.39
    POSITIVE LOGITS
     PCB
    0.41
     (“
    0.40
    PCB
    0.40
     talks
    0.39
     cambiando
    0.38
     Situ
    0.38
     certificates
    0.38
    值
    0.37
    WT
    0.37
     toes
    0.37
    Activations Density 0.027%

    No Known Activations