© 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. 3216
    Prev
    Next
    INDEX
    Explanations

    Hominins, engines, view, weight

    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
     различными
    1.14
    setShow
    1.12
     количе
    1.12
     electrolyte
    1.10
     Thoroughbred
    1.09
     enumeration
    1.08
     electrolytes
    1.07
    <unused2121>
    1.06
    이며
    1.04
     meditations
    1.02
    POSITIVE LOGITS
    Რ
    1.13
    లో
    1.10
     Hvis
    1.09
    ר
    1.08
    こ
    1.08
    тере
    1.05
    Hvis
    1.05
    平成
    1.04
    nless
    1.03
     strconv
    1.02
    Activations Density 0.024%

    No Known Activations