© 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. 14178
    Prev
    Next
    INDEX
    Explanations

    explaining why or potential use

    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
     enfermedad
    2.06
     princesa
    2.02
    𝓷
    1.91
     doença
    1.89
     receber
    1.85
     bệnh
    1.85
    勮
    1.79
     całkow
    1.78
     apariencia
    1.78
     permanece
    1.77
    POSITIVE LOGITS
    ograp
    1.51
    grep
    1.49
    mars
    1.46
    matches
    1.42
    nus
    1.40
    „
    1.39
    crib
    1.34
    matching
    1.34
    chool
    1.34
    category
    1.33
    Activations Density 0.003%

    No Known Activations