© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 4917
    Prev
    Next
    INDEX
    Explanations

    reflection, instructions, then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     ý
    0.74
    currently
    0.70
    ingan
    0.61
     своє
    0.59
    idea
    0.58
     Augen
    0.58
     സ്ഥാന
    0.58
     Ministro
    0.57
     étapes
    0.57
    points
    0.57
    POSITIVE LOGITS
     Esp
    0.51
     sizzling
    0.50
    闿
    0.49
     law
    0.49
    ឱ្យ
    0.46
    ари
    0.46
     Negros
    0.45
    해도
    0.45
    EDU
    0.45
     соли
    0.44
    Activations Density 0.000%

    No Known Activations