© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12539
    Prev
    Next
    INDEX
    Explanations

    parenthesis followed by double asterisk

    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
     sy
    2.51
    एस
    2.44
     maks
    2.42
    渟
    2.40
        
    2.38
     ancest
    2.35
    پ
    2.34
    SED
    2.34
     तै
    2.32
    ্কর
    2.32
    POSITIVE LOGITS
    ⃛
    2.87
    렀
    2.72
     العالمين
    2.62
    anova
    2.61
    nal
    2.54
    InputElement
    2.52
    ೮
    2.52
    ើ
    2.51
    ුව
    2.50
     ControllerBase
    2.49
    Activations Density 0.022%

    No Known Activations