© 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. 587
    Prev
    Next
    INDEX
    Explanations

    code symbols and programming terms

    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
     (
    1.02
     (“
    1.01
     rigorously
    1.00
     meticulously
    0.98
     your
    0.96
    ,
    0.96
     amidst
    0.94
     parting
    0.94
     terrestrial
    0.93
     prominent
    0.92
    POSITIVE LOGITS
    error
    1.13
    msg
    1.12
    max
    1.10
    p
    1.08
    cmp
    1.04
    cwd
    1.02
    cb
    1.02
    bf
    1.02
    uuid
    1.01
    R
    1.01
    Activations Density 0.667%

    No Known Activations