© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37085
    Prev
    Next
    INDEX
    Explanations

    specialized terms and concepts

    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
    edRight
    0.60
     وکړئ
    0.58
    忉
    0.51
    夆
    0.49
    轲
    0.48
    ljen
    0.47
    𝓎
    0.47
    abilità
    0.47
    দিনে
    0.47
    nessy
    0.47
    POSITIVE LOGITS
     there
    0.49
     vessels
    0.49
     work
    0.48
     research
    0.47
     cells
    0.47
     <
    0.45
     big
    0.44
     modified
    0.44
     cell
    0.43
     visited
    0.43
    Activations Density 0.002%

    No Known Activations