© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146507
    Prev
    Next
    INDEX
    Explanations

    costly ways, resolution, structure

    np_acts-logits-general · gemini-2.5-flash-lite

    things are perceived or fundamental

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    申请
    0.41
    单个
    0.41
     服务
    0.41
    सौ
    0.41
    𝗴
    0.41
    喆
    0.41
     單
    0.40
    ॢ
    0.39
    超过
    0.39
    pageNum
    0.39
    POSITIVE LOGITS
     ausgestattet
    0.52
     rechte
    0.50
     eingesetzt
    0.48
     eingesch
    0.48
     verwendet
    0.48
     gelegen
    0.48
     replicates
    0.47
     bristles
    0.47
     entstanden
    0.47
     verwendeten
    0.46
    Activations Density 0.000%

    No Known Activations