Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41044
    Prev
    Next
    INDEX
    Explanations

    radio transmissions, Signal Protocol, expressing excitement

    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_29_width_65k_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
    तावनी
    0.72
     einge
    0.72
     hidrográf
    0.66
     asiento
    0.66
     duen
    0.66
    市场的
    0.65
    ValArr
    0.65
    焓
    0.64
     kú
    0.64
    ighth
    0.64
    POSITIVE LOGITS
     Diversity
    0.70
     luckily
    0.68
     kay
    0.68
     нас
    0.65
     Kay
    0.65
     AX
    0.65
    ..
    0.64
     thankfully
    0.64
    애
    0.63
    Diversity
    0.63
    Activations Density 0.003%

    No Known Activations