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. 22-GEMMASCOPE-2-RES-16K
    4. 283
    Prev
    Next
    INDEX
    Explanations

    a new

    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_22_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
    C
    0.49
    H
    0.46
    Y
    0.45
    A
    0.44
    E
    0.42
    In
    0.42
    I
    0.42
     Iterate
    0.41
     Complexity
    0.41
    a
    0.40
    POSITIVE LOGITS
     veritable
    0.65
     remarkable
    0.64
     whopping
    0.63
     wonderful
    0.63
     tremendous
    0.62
     fiery
    0.62
     unmistakable
    0.62
     impressive
    0.62
     spacious
    0.61
     glittering
    0.61
    Activations Density 7.369%

    No Known Activations