© 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. 200463
    Prev
    Next
    INDEX
    Explanations

    core capabilities and ideas

    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
    मैंने
    0.48
     malignancy
    0.46
    Í
    0.46
    ⺀
    0.45
    ัตว์
    0.44
     kanker
    0.44
    zoic
    0.43
    暴
    0.42
    分為
    0.42
    斯
    0.41
    POSITIVE LOGITS
     needed
    0.51
     Athena
    0.50
     upstream
    0.49
     handover
    0.46
     technically
    0.45
    listening
    0.45
    어야
    0.45
     amend
    0.44
     aesthetically
    0.43
     astronom
    0.43
    Activations Density 0.005%

    No Known Activations