© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37188
    Prev
    Next
    INDEX
    Explanations

    phrases starting with common words

    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
    േന
    0.49
    你需要
    0.45
     Scholarships
    0.45
    跟你
    0.44
    和你
    0.44
     Introduction
    0.43
    ྰ
    0.43
    อน
    0.43
    关注
    0.42
     तुम्हाला
    0.42
    POSITIVE LOGITS
     Tric
    0.49
    itre
    0.48
     p
    0.48
     wicked
    0.47
     scall
    0.47
     Treg
    0.46
     pim
    0.46
     condom
    0.46
     walled
    0.45
     saber
    0.45
    Activations Density 0.000%

    No Known Activations