© 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. 10986
    Prev
    Next
    INDEX
    Explanations

    moles of chemical substances

    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
    Ს
    0.54
    锑
    0.52
    Გ
    0.50
    拍摄
    0.50
    ახებ
    0.48
    比特币
    0.46
    Ფ
    0.46
    时
    0.46
    фициа
    0.45
    Ი
    0.44
    POSITIVE LOGITS
     சார்ந்த
    0.42
     whose
    0.42
     còn
    0.42
     ki
    0.42
     N
    0.41
     không
    0.41
    yout
    0.41
     sống
    0.41
     rồi
    0.40
     zur
    0.40
    Activations Density 0.010%

    No Known Activations