© 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. 101746
    Prev
    Next
    INDEX
    Explanations

    describing state or purpose

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

    outdated versioning

    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
     chute
    0.43
     grasses
    0.41
     الرغم
    0.41
     Lightfoot
    0.40
    撥
    0.40
     unilateral
    0.39
     footing
    0.39
     Slate
    0.38
     hogares
    0.38
     sawdust
    0.38
    POSITIVE LOGITS
     युग
    0.48
     Akademie
    0.47
     будет
    0.46
     મળશે
    0.46
    Ζ
    0.46
    รายละเอียด
    0.46
    znacz
    0.46
     Университе
    0.46
     ще
    0.45
     лише
    0.44
    Activations Density 0.002%

    No Known Activations