© 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. 31-GEMMASCOPE-2-RES-262K
    7. 84787
    Prev
    Next
    INDEX
    Explanations

    technical explanations and planning

    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_31_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
     Hacer
    0.53
     algéb
    0.50
    िकुलर
    0.50
     énfasis
    0.50
    儉
    0.50
     autonomia
    0.48
    懟
    0.48
     केमिस्ट्री
    0.47
     autón
    0.47
     Emphasis
    0.46
    POSITIVE LOGITS
    、
    0.48
     หลังจาก
    0.44
    这时
    0.43
    元
    0.41
    movie
    0.41
    payload
    0.41
    pictures
    0.41
    pollution
    0.40
    sky
    0.39
     heart
    0.38
    Activations Density 0.013%

    No Known Activations