© 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. 2819
    Prev
    Next
    INDEX
    Explanations

    negative or vulgar contexts

    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
     ఇతర
    0.83
     các
    0.81
    <unused687>
    0.79
     ―
    0.75
    rées
    0.74
     अन्य
    0.74
    listof
    0.74
    <unused566>
    0.73
    <unused244>
    0.73
    లతో
    0.72
    POSITIVE LOGITS
     douche
    0.83
     cancer
    0.74
     acne
    0.72
     tonight
    0.68
     cuddle
    0.67
     drunk
    0.67
     please
    0.66
     fucking
    0.65
    ?)
    0.65
     potty
    0.64
    Activations Density 0.001%

    No Known Activations