Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8227
    Prev
    Next
    INDEX
    Explanations

    words and phrases

    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_9_width_262k_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
    هُ
    0.96
    and
    0.94
    ्ले
    0.92
    οι
    0.90
    8
    0.84
    7
    0.84
    developing
    0.83
    β
    0.83
    कार्य
    0.82
    លើ
    0.81
    POSITIVE LOGITS
     Saltar
    1.13
     kullanıl
    1.11
     washable
    1.10
     Kullan
    1.08
     isomers
    1.06
    maal
    1.06
     što
    1.03
     bestimmt
    1.02
     packets
    1.02
     galera
    1.02
    Activations Density 0.103%

    No Known Activations