© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 8731
    Prev
    Next
    INDEX
    Explanations

    asking to open files or directories

    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
    تبر
    1.32
     Citizenship
    1.27
     예술
    1.21
     equating
    1.21
    ت
    1.18
     UAV
    1.18
     OPEC
    1.17
    т
    1.14
     sentenced
    1.13
     ingested
    1.13
    POSITIVE LOGITS
     prüfen
    1.15
     treten
    1.04
    𝖑
    1.03
    𝖒
    1.03
     puertas
    1.02
    事は
    1.02
     gabinete
    1.01
     durant
    1.01
    angebot
    1.00
    FA
    1.00
    Activations Density 0.004%

    No Known Activations