© 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. 43479
    Prev
    Next
    INDEX
    Explanations

    emphatic discourse

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

    temporal or conditional phrases

    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
    。
    0.49
    ˗
    0.48
    ।
    0.47
     হইতেছিল
    0.44
     that
    0.44
    ከላከ
    0.44
    ูก
    0.42
     a
    0.42
    핀
    0.41
    λ
    0.41
    POSITIVE LOGITS
    (!)
    0.98
     (!)
    0.92
    !!!!!
    0.79
    !!!
    0.75
     sooo
    0.73
    !!!!
    0.73
     soooo
    0.73
    !!!!!!
    0.70
    !
    0.70
     ONLY
    0.70
    Activations Density 0.077%

    No Known Activations