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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 423
    Prev
    Next
    INDEX
    Explanations

    table summarizing differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     };
    0.57
    मॉन
    0.53
     implies
    0.50
     AI
    0.50
     tech
    0.49
    alian
    0.49
     flora
    0.48
     pro
    0.48
     s
    0.48
     ’
    0.48
    POSITIVE LOGITS
    ----------------
    2.23
    ________________
    1.68
    ================
    1.57
    ————————————————
    1.56
    ---------------
    1.50
    -------
    1.46
    -------------
    1.44
    ----------
    1.41
    -----
    1.40
    ………………………………
    1.39
    Activations Density 0.092%

    No Known Activations