© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8304
    Prev
    Next
    INDEX
    Explanations

    opportunities and options

    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
    𝐂
    2.48
    어
    2.28
    𝐁
    2.25
     unleashed
    2.17
    า
    2.14
    an
    2.13
    在
    2.13
    𝐀
    2.13
    ούς
    2.11
    ீர
    2.10
    POSITIVE LOGITS
    ن
    2.41
    en
    2.30
    lardan
    2.29
    ة
    2.28
    н
    2.26
    ally
    2.25
    loser
    2.22
    nearest
    2.22
     万元
    2.19
    l
    2.18
    Activations Density 0.302%

    No Known Activations