Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 108309
    Prev
    Next
    INDEX
    Explanations

    security and technical terms

    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
     metabolite
    0.51
    鉞
    0.50
    u
    0.47
    _
    0.45
     propagates
    0.44
    ものの
    0.43
     indications
    0.42
    лив
    0.42
     With
    0.41
    하지만
    0.41
    POSITIVE LOGITS
     дальней
    0.51
     ८
    0.49
    anton
    0.46
     автоном
    0.46
     данной
    0.45
    ismarck
    0.44
    Longrightarrow
    0.44
     aul
    0.44
     ۸
    0.43
    antes
    0.43
    Activations Density 0.015%

    No Known Activations