© 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. 69044
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce conclusions

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

    numbers, punctuation, and foreign characters

    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
     gentleman
    0.47
     transactional
    0.47
     planter
    0.46
     estrict
    0.45
     chore
    0.45
    )[
    0.45
    बाग
    0.44
     /ˈ
    0.44
     pravi
    0.44
     دي
    0.44
    POSITIVE LOGITS
    ール
    0.52
    чной
    0.46
    chluss
    0.46
    装置
    0.45
    懋
    0.43
    ന്ധ
    0.43
    жного
    0.42
    ਹੀਂ
    0.42
    ит
    0.42
    ъем
    0.42
    Activations Density 0.001%

    No Known Activations