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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7360
    Prev
    Next
    INDEX
    Explanations

    Process and product development

    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
    yla
    1.22
    饕
    1.17
    etr
    1.16
     kabar
    1.15
    ค่า
    1.12
    攷
    1.10
    ต้องการ
    1.10
    িং
    1.10
     yī
    1.08
    niv
    1.07
    POSITIVE LOGITS
    ма
    1.21
    Ду
    1.18
    credibly
    1.18
     brakes
    1.15
    𝚆
    1.14
     mínimos
    1.12
    NaBH
    1.09
    ここでは
    1.09
    莗
    1.08
     начало
    1.07
    Activations Density 0.000%

    No Known Activations