© 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. 203974
    Prev
    Next
    INDEX
    Explanations

    status updates after certain words

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

    Dungeons & Dragons fluency

    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
    应该
    0.53
     આરોપી
    0.53
    发射
    0.51
    ánico
    0.49
    ersonic
    0.48
    骶
    0.46
    應該
    0.45
    ing
    0.45
     preferencias
    0.45
    ด
    0.45
    POSITIVE LOGITS
     Cay
    0.46
     changeable
    0.44
     لعب
    0.44
     interplay
    0.44
     trope
    0.44
     lokal
    0.44
     disturbance
    0.43
     wander
    0.43
     cove
    0.43
    POE
    0.42
    Activations Density 0.000%

    No Known Activations