© 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. 3218
    Prev
    Next
    INDEX
    Explanations

    golden hour, golden retriever, silver emblem

    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
    н
    1.40
    ات
    1.40
     Crohn
    1.21
    ר
    1.20
     আত্মহত্যা
    1.14
     violently
    1.13
    
    1.12
    ン
    1.12
     жар
    1.10
     wouldn
    1.09
    POSITIVE LOGITS
     compelled
    1.18
    koliko
    1.17
    levant
    1.15
    horas
    1.10
    accia
    1.08
    łączyć
    1.07
    ové
    1.04
    pesar
    1.04
    geq
    1.02
    be
    1.01
    Activations Density 0.081%

    No Known Activations