© 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. 1275
    Prev
    Next
    INDEX
    Explanations

    could only

    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
     kunna
    1.92
     poder
    1.70
     poter
    1.70
    การ
    1.68
     pouvoir
    1.64
    क
    1.62
    𝑖
    1.62
     kunne
    1.61
    𝐢
    1.61
    𝐞
    1.57
    POSITIVE LOGITS
     withstand
    2.43
     afford
    2.42
    adians
    2.41
    檛
    2.23
     easily
    2.18
    berra
    2.12
    ADIAN
    2.08
    ilever
    2.08
    vasser
    2.01
     afforded
    2.01
    Activations Density 0.568%

    No Known Activations