© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 647
    Prev
    Next
    INDEX
    Explanations

    roles and persons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     difer
    0.93
     Laat
    0.81
     decirlo
    0.81
    every
    0.80
    อต
    0.79
     کشورهای
    0.79
     laat
    0.78
    墟
    0.78
     fonctionnement
    0.77
    юць
    0.77
    POSITIVE LOGITS
    '
    1.05
     ஒருவர்
    0.92
     द्वारा
    0.91
    ’
    0.84
     இருவரும்
    0.82
    narr
    0.80
     interviewee
    0.79
     protagon
    0.78
     chef
    0.78
    Role
    0.78
    Activations Density 0.673%

    No Known Activations