© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70092
    Prev
    Next
    INDEX
    Explanations

    she is / he is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_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
    支持
    0.83
    応援
    0.76
    łon
    0.75
     عليكم
    0.75
    陛
    0.74
     strop
    0.73
    给我们
    0.72
     capacitación
    0.72
    ítani
    0.72
    <0x81>
    0.72
    POSITIVE LOGITS
     nghĩa
    1.99
     Mars
    1.96
     contains
    1.90
     Heimat
    1.89
     formes
    1.86
     decomposes
    1.84
     amis
    1.83
    oblasts
    1.82
     exfoli
    1.82
     loses
    1.81
    Activations Density 0.003%

    No Known Activations