© 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. 17-GEMMASCOPE-2-RES-16K
    7. 9465
    Prev
    Next
    INDEX
    Explanations

    reempl / replaced / equivalence

    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_17_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
     Probation
    0.71
    expires
    0.67
    なければ
    0.67
    yeah
    0.66
    scode
    0.66
    pre
    0.65
     scopo
    0.64
     є
    0.64
     alleine
    0.64
    的前提
    0.64
    POSITIVE LOGITS
     equivalent
    0.89
     barbaric
    0.86
    Rename
    0.85
     flamboyant
    0.85
     equivalence
    0.82
     reempl
    0.80
     barbar
    0.80
     ghostly
    0.80
     perceives
    0.78
     replaced
    0.78
    Activations Density 0.223%

    No Known Activations