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. 6118
    Prev
    Next
    INDEX
    Explanations

    stream, beam, scheme

    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
     ܘ
    0.69
    Gather
    0.69
    gather
    0.69
     Earle
    0.67
    নারায়ণ
    0.67
    ∑</
    0.67
     পুণ
    0.66
    晤
    0.66
    ChatMessage
    0.66
    ša
    0.66
    POSITIVE LOGITS
    hedron
    0.73
    Sent
    0.67
     Sent
    0.65
    avu
    0.65
    が高い
    0.64
     Sino
    0.63
    interpolate
    0.62
    ive
    0.62
     Holes
    0.62
    ruf
    0.62
    Activations Density 0.004%

    No Known Activations