© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1149
    Prev
    Next
    INDEX
    Explanations

    code execution

    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_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
     horrifying
    0.85
     dreaded
    0.83
     incapac
    0.83
     horrific
    0.78
     ravaged
    0.78
     humild
    0.76
     heinous
    0.75
    ">(</
    0.75
     fateful
    0.75
     harmonization
    0.75
    POSITIVE LOGITS
    y
    0.79
    if
    0.74
    yaw
    0.69
    Vec
    0.68
    kWh
    0.67
    rnd
    0.66
    KM
    0.66
    chi
    0.66
    dow
    0.66
    MM
    0.66
    Activations Density 0.264%

    No Known Activations