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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 56594
    Prev
    Next
    INDEX
    Explanations

    Botsonic AI

    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_65k_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
    لە
    0.47
    કામાં
    0.44
     causado
    0.44
     audioElement
    0.43
     বরাত
    0.43
    容
    0.43
    ያው
    0.42
    簟
    0.42
    の名前
    0.42
    靗
    0.42
    POSITIVE LOGITS
    years
    0.48
    ↵↵
    0.44
     years
    0.44
    stom
    0.42
    ideo
    0.41
    net
    0.41
     amicable
    0.41
    atility
    0.41
     CEOs
    0.41
     undang
    0.41
    Activations Density 0.007%

    No Known Activations