© 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-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 11894
    Prev
    Next
    INDEX
    Explanations

    is this thought true

    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
     குழந்தைகளின்
    0.99
     ひ
    0.98
    ieuses
    0.97
     자
    0.94
    及其
    0.93
     içine
    0.93
    􀍷
    0.93
    𒆝
    0.93
    HtIdx
    0.93
     بإ
    0.93
    POSITIVE LOGITS
     DNA
    0.86
     Behavioral
    0.66
    DNA
    0.65
     behavior
    0.65
     behavioral
    0.64
    disciplinary
    0.61
     setup
    0.60
    output
    0.60
    辑
    0.60
    keeper
    0.59
    Activations Density 0.003%

    No Known Activations