© 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-16K
    7. 758
    Prev
    Next
    INDEX
    Explanations

    question/answer prompts

    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_16k_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
     manifolds
    0.76
     studying
    0.73
     experimentation
    0.70
     delaying
    0.69
     experimenting
    0.68
     situations
    0.67
     immortality
    0.67
    弼
    0.64
    ways
    0.64
     orchestras
    0.63
    POSITIVE LOGITS
     gesamte
    1.19
     этот
    1.15
     această
    1.08
     해당
    1.07
     този
    1.02
     Этот
    0.99
     tomto
    0.97
     ovaj
    0.97
    यह
    0.97
     данный
    0.95
    Activations Density 0.323%

    No Known Activations