© 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. 1422
    Prev
    Next
    INDEX
    Explanations

    specific token followed by specific word

    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
    ">•
    1.20
    чер
    1.16
     Oberfläche
    1.14
     univariate
    1.12
     forKey
    1.12
     commend
    1.09
     এস
    1.08
     oppervlak
    1.08
     gratuitement
    1.08
     défi
    1.08
    POSITIVE LOGITS
    ो
    1.29
    િ
    1.23
    aj
    1.19
    ne
    1.19
    ும்போது
    1.16
    volving
    1.11
    en
    1.08
    ان
    1.03
    ే
    1.03
    at
    1.03
    Activations Density 0.000%

    No Known Activations