© 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. 4088
    Prev
    Next
    INDEX
    Explanations

    whole word, cloud computing, captivating, held in high regard, test of courage, retire, eat, applications, shout it loud, falter

    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
     cabel
    0.46
     helix
    0.42
     cauliflower
    0.41
     carat
    0.40
     ‘
    0.38
     optical
    0.38
     handel
    0.37
     지원
    0.37
     goblet
    0.37
     support
    0.36
    POSITIVE LOGITS
    Да
    0.38
    හෙ
    0.38
    દિવસ
    0.37
    𝑰
    0.37
    /~
    0.37
    ન
    0.36
    modifier
    0.35
    hôpital
    0.35
    אַ
    0.34
    äft
    0.34
    Activations Density 0.000%

    No Known Activations