© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31767
    Prev
    Next
    INDEX
    Explanations

    grew up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    強制
    0.44
    出身
    0.43
     childhood
    0.41
     sculpture
    0.39
     trouble
    0.38
     inherited
    0.38
     পাঠানো
    0.38
    置
    0.38
     educação
    0.38
    ުން
    0.37
    POSITIVE LOGITS
    hearing
    0.55
     mendengar
    0.50
     hearing
    0.49
     рядом
    0.46
    Hearing
    0.46
     naast
    0.46
     yanında
    0.45
     HEARING
    0.45
    idol
    0.44
    knowing
    0.44
    Activations Density 0.002%

    No Known Activations