© 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. 13-GEMMASCOPE-2-RES-65K
    7. 585
    Prev
    Next
    INDEX
    Explanations

    maintaining states and conditions

    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
    0.98
     (
    0.98
     уже
    0.97
    ,
    0.94
     S
    0.94
    to
    0.92
     R
    0.92
    次に
    0.90
     inicio
    0.89
     предстоя
    0.88
    POSITIVE LOGITS
     steadfast
    1.99
     faithfulness
    1.81
     constancy
    1.77
     unchanged
    1.75
     abreast
    1.74
     Maintaining
    1.73
     Maintains
    1.68
     unchanging
    1.67
     composure
    1.66
     afloat
    1.65
    Activations Density 0.753%

    No Known Activations