© 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. 3401
    Prev
    Next
    INDEX
    Explanations

    branch from, dato para, default is

    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
     இந்தக்
    1.00
    在这种
    0.98
    ِر
    0.98
    䢍
    0.96
    Dieser
    0.94
    Within
    0.94
    㥽
    0.93
     &/
    0.91
    Whatever
    0.90
     Interestingly
    0.90
    POSITIVE LOGITS
     again
    0.87
     ebenfalls
    0.86
    вера
    0.83
     near
    0.70
     also
    0.68
     about
    0.68
     medium
    0.67
     around
    0.65
     ele
    0.65
     along
    0.64
    Activations Density 0.718%

    No Known Activations