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. 13
    Prev
    Next
    INDEX
    Explanations

    contractions like it's

    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
    M
    0.65
    ,
    0.63
    H
    0.63
    :
    0.61
    C
    0.61
    D
    0.60
    С
    0.60
    Con
    0.60
    。
    0.59
    K
    0.58
    POSITIVE LOGITS
     albeit
    0.99
     haha
    0.91
     but
    0.88
     huh
    0.86
     brimming
    0.85
     relentless
    0.82
     unwavering
    0.82
     odnosno
    0.80
     unsettling
    0.78
     heartbreaking
    0.78
    Activations Density 2.816%

    No Known Activations