© 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. 25069
    Prev
    Next
    INDEX
    Explanations

    but**

    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
    。
    0.46
     但是
    0.45
    ्रे
    0.39
     由于
    0.39
     Ấ
    0.39
    ಾರ್
    0.38
    }.
    0.38
    છી
    0.38
     butane
    0.38
     但
    0.37
    POSITIVE LOGITS
    eliers
    0.45
     Juris
    0.45
    emploi
    0.43
     ingen
    0.42
     łat
    0.41
     madres
    0.41
    일리
    0.41
     osnov
    0.40
     acept
    0.40
     commencent
    0.40
    Activations Density 0.005%

    No Known Activations