Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1012
    Prev
    Next
    INDEX
    Explanations

    after that date

    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
    ellants
    0.77
    acea
    0.73
     triglyceride
    0.71
    exam
    0.71
    holm
    0.71
    squeeze
    0.70
    indle
    0.68
    ][/
    0.68
    3
    0.68
    trial
    0.67
    POSITIVE LOGITS
     أو
    1.05
     או
    0.94
     مع
    0.82
     По
    0.80
     или
    0.78
     في
    0.77
     overboard
    0.76
     atau
    0.75
     increíble
    0.74
    生
    0.74
    Activations Density 0.025%

    No Known Activations