© 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. 111298
    Prev
    Next
    INDEX
    Explanations

    compares prices

    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
    -
    0.49
    ',
    0.45
    _
    0.45
     la
    0.44
     l
    0.44
    ;
    0.43
     arbitr
    0.42
     Contin
    0.42
     Austin
    0.42
     f
    0.41
    POSITIVE LOGITS
     сте
    0.54
     볼
    0.54
    sadpoetry
    0.52
     تَ
    0.52
     سخت
    0.52
     वायरिंग
    0.51
     టిప్పు
    0.51
     보기
    0.49
     изда
    0.49
     тип
    0.49
    Activations Density 0.007%

    No Known Activations