© 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. 1138
    Prev
    Next
    INDEX
    Explanations

    freezes weights

    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
     manifestly
    1.02
     illustrious
    1.01
     fulfills
    0.98
     multitud
    0.98
     defies
    0.97
    <unused1028>
    0.97
     biotechnology
    0.97
     Lyapunov
    0.96
    ড়ান্ত
    0.96
     deployments
    0.95
    POSITIVE LOGITS
    te
    1.11
    l
    0.95
    f
    0.95
    ter
    0.90
    ди
    0.86
    ה
    0.85
    葚
    0.82
    cre
    0.81
    ন
    0.81
     doar
    0.80
    Activations Density 0.188%

    No Known Activations