© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 610
    Prev
    Next
    INDEX
    Explanations

    informational purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     추가
    1.48
    ੲ
    1.42
    푥
    1.41
     buttonAnimation
    1.37
     다양한
    1.36
     quantifiable
    1.35
     가능한
    1.35
     semantics
    1.32
     nDims
    1.30
     관련
    1.30
    POSITIVE LOGITS
     [
    1.43
     יה
    1.34
     saith
    1.28
     unto
    1.19
     verily
    1.15
     JESUS
    1.14
     God
    1.11
     LORD
    1.10
     Scripture
    1.10
    unto
    1.10
    Activations Density 0.436%

    No Known Activations