© 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-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 132
    Prev
    Next
    INDEX
    Explanations

    special or others

    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_17_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
    ของ
    1.58
    3
    1.44
    4
    1.44
    2
    1.42
    1
    1.41
    及
    1.39
    ในปี
    1.38
    在
    1.36
    部分
    1.34
    和
    1.33
    POSITIVE LOGITS
     nuanced
    2.08
     sophisticated
    2.02
     memorable
    1.93
     unforgettable
    1.93
     pristine
    1.88
     timeless
    1.87
     honest
    1.86
     mindfulness
    1.86
     mindless
    1.86
     subjective
    1.85
    Activations Density 0.168%

    No Known Activations