© 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. 13-GEMMASCOPE-2-RES-65K
    4. 2327
    Prev
    Next
    INDEX
    Explanations

    end of phrase

    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_13_width_65k_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
     कंपनियां
    1.44
    Eds
    1.36
     reconoc
    1.34
    ロシア
    1.33
    İK
    1.32
     hospitales
    1.31
    僕
    1.30
     Parlament
    1.27
    য্
    1.22
     paesi
    1.22
    POSITIVE LOGITS
     deple
    1.34
     but
    1.30
    加えて
    1.27
    luster
    1.26
    fueled
    1.26
     atop
    1.20
    跎
    1.19
     against
    1.16
     outweighs
    1.16
     outweighed
    1.15
    Activations Density 0.000%

    No Known Activations