© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3269
    Prev
    Next
    INDEX
    Explanations

    acronym qualifiers and their fields

    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
     /
    0.66
     ("
    0.64
    <sup>
    0.61
     ah
    0.60
     derivatives
    0.59
     também
    0.59
     *
    0.59
     "
    0.58
    ക്
    0.58
     buch
    0.58
    POSITIVE LOGITS
    ﺗ
    0.91
    埋
    0.80
     Improving
    0.78
     Establishing
    0.78
     ايجاد
    0.78
    تح
    0.78
    )$.
    0.78
    Improving
    0.77
    Improve
    0.77
    !!)
    0.75
    Activations Density 0.146%

    No Known Activations