© 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. 100118
    Prev
    Next
    INDEX
    Explanations

    percentage estimation

    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
    遴
    0.50
     inorder
    0.48
    ਰ
    0.45
    丰富的
    0.45
     համ
    0.44
     articulated
    0.43
    rets
    0.42
     გვ
    0.42
     همد
    0.42
     seminal
    0.42
    POSITIVE LOGITS
     अदर
    0.48
    d
    0.47
     abrupt
    0.46
     Unter
    0.45
    io
    0.43
     engulf
    0.43
    Patient
    0.43
    Under
    0.42
    Voltage
    0.42
    een
    0.42
    Activations Density 0.001%

    No Known Activations