© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 14672
    Prev
    Next
    INDEX
    Explanations

    genetic variation

    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
     parsed
    1.30
     choice
    1.15
    秆
    1.11
    GetInstance
    1.08
     amends
    1.07
     reunir
    1.07
     connu
    1.07
    Ook
    1.06
     navController
    1.06
    বিষ্য
    1.06
    POSITIVE LOGITS
    ت
    1.22
    า
    1.17
    ავ
    1.14
    thisobject
    1.10
    an
    1.09
    ideon
    1.09
    िक
    1.08
    െ
    1.07
    मधील
    1.06
    اً
    1.05
    Activations Density 0.001%

    No Known Activations