© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41561
    Prev
    Next
    INDEX
    Explanations

    capacity, change, current, lattice, look

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ｇ
    0.46
    Ｅ
    0.44
    ﻨ
    0.44
     guessing
    0.43
     සී
    0.43
     درجه
    0.42
     accomplishes
    0.42
    ИН
    0.42
    Ｉ
    0.41
    USTOM
    0.41
    POSITIVE LOGITS
     bimod
    0.48
    bies
    0.46
     datasets
    0.43
     silhouettes
    0.43
                                  
    0.43
     haar
    0.42
     inscriptions
    0.42
     stojí
    0.42
     {}
    0.42
    dets
    0.42
    Activations Density 0.001%

    No Known Activations