© 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. 41951
    Prev
    Next
    INDEX
    Explanations

    resilience, reliance, deviations, input

    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
     luxuries
    0.45
     mob
    0.40
     във
    0.40
     FMC
    0.38
     ~
    0.37
    шуу
    0.37
     экономи
    0.37
     поради
    0.35
    holding
    0.35
     FPR
    0.35
    POSITIVE LOGITS
     Frü
    0.49
     Asalamualaikum
    0.48
    tä
    0.47
    𒂊
    0.47
    ösungen
    0.47
    lja
    0.47
    ংকা
    0.47
     écart
    0.45
     drücken
    0.45
    汋
    0.45
    Activations Density 0.002%

    No Known Activations