© 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. 1506
    Prev
    Next
    INDEX
    Explanations

    relates different positions

    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
    i
    1.48
    ی
    1.22
     গিয়ে
    1.16
    an
    1.15
    й
    1.13
    今後の
    1.06
    \[
    1.04
    йся
    1.04
    ed
    1.02
    ي
    1.02
    POSITIVE LOGITS
     halfway
    1.44
     junkie
    1.20
    র্ন
    1.20
     пол
    1.16
     earl
    1.15
    बीयत
    1.14
     jealous
    1.13
     loudly
    1.13
     ayurved
    1.13
    tta
    1.10
    Activations Density 0.001%

    No Known Activations