© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1254
    Prev
    Next
    INDEX
    Explanations

    improvements and explanations

    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_13_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
    缀
    0.61
     certain
    0.58
    ister
    0.57
    ros
    0.57
    שהו
    0.56
    ander
    0.56
    sometimes
    0.56
    ere
    0.54
    __(
    0.54
    wee
    0.54
    POSITIVE LOGITS
     обнов
    1.22
     nuova
    1.20
     지속
    1.19
     renewed
    1.13
     reinvigor
    1.13
     inov
    1.13
     최고의
    1.12
     unsurpassed
    1.11
     redesigned
    1.09
     rejuvenated
    1.09
    Activations Density 0.183%

    No Known Activations