© 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. 3477
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
     connaître
    1.05
     essence
    0.97
    ה
    0.96
    适用于
    0.92
    erness
    0.92
    <0x80>
    0.92
    for
    0.91
     birbir
    0.90
    forall
    0.90
     genere
    0.89
    POSITIVE LOGITS
    殊
    1.18
    десят
    1.10
    ধ্য
    1.00
     pocos
    0.98
    mals
    0.96
     paio
    0.95
     poucos
    0.94
    зку
    0.94
    maßen
    0.94
     opposites
    0.93
    Activations Density 0.076%

    No Known Activations