© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2597
    Prev
    Next
    INDEX
    Explanations

    Tamil actors

    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
     باست
    0.89
    µ
    0.88
    R
    0.88
    螢
    0.86
    -(
    0.86
    peria
    0.85
    T
    0.85
    ./
    0.82
     بالم
    0.81
    ৪০
    0.81
    POSITIVE LOGITS
     gesamte
    1.44
     unsere
    1.41
     kommt
    1.36
     ganze
    1.34
     adenine
    1.28
     werde
    1.27
     Frankreich
    1.26
     stoff
    1.26
     SULF
    1.26
     wichtig
    1.25
    Activations Density 0.031%

    No Known Activations