© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14196
    Prev
    Next
    INDEX
    Explanations

    spreadsheet functions

    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_7_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
    MainBinding
    2.47
     駅
    2.35
    WeatherData
    2.35
    วรร
    2.31
     thisComponent
    2.30
     Ile
    2.30
     ਘ
    2.28
    lays
    2.27
     河
    2.27
    லி
    2.26
    POSITIVE LOGITS
    फत
    2.33
    te
    2.16
     tors
    2.09
    দীর্ঘ
    2.07
    いく
    2.05
    рых
    2.03
    Ѳ
    2.02
    मधून
    2.00
    rao
    2.00
    čke
    1.99
    Activations Density 0.032%

    No Known Activations