© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84457
    Prev
    Next
    INDEX
    Explanations

    requirements or specifications

    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_40_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
     NSUTF
    0.40
    ąpi
    0.40
     ফুটে
    0.40
    綴
    0.39
     čemu
    0.38
    ində
    0.38
    ähn
    0.38
     uży
    0.37
     পুরা
    0.37
    钡
    0.37
    POSITIVE LOGITS
     Required
    0.44
     required
    0.42
    Civil
    0.41
    Required
    0.41
    Mechanical
    0.41
     Mechanical
    0.39
    quis
    0.38
    Must
    0.37
    required
    0.37
     রাশ
    0.36
    Activations Density 0.003%

    No Known Activations