© 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. 170128
    Prev
    Next
    INDEX
    Explanations

    bond loan

    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
     두
    0.40
     أكبر
    0.38
    ست
    0.38
    새
    0.37
    兩人
    0.36
     Planung
    0.36
    ält
    0.36
    5
    0.36
    สอง
    0.35
     sämt
    0.35
    POSITIVE LOGITS
    arabangsa
    0.48
    nocześnie
    0.46
     初始化
    0.46
    वून
    0.46
    देशी
    0.46
    larak
    0.45
    nemen
    0.45
     pleasant
    0.45
     dour
    0.45
    iyaki
    0.45
    Activations Density 0.009%

    No Known Activations