© 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. 127440
    Prev
    Next
    INDEX
    Explanations

    related to or following rates

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

    understanding requirements

    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
    ！”
    0.58
    ”，
    0.52
    ”。
    0.52
    缑
    0.49
    ❞
    0.48
    骑
    0.46
    瓷
    0.46
    橐
    0.46
    。”
    0.45
    ！」
    0.45
    POSITIVE LOGITS
     relatives
    0.48
     concili
    0.47
     dint
    0.47
     realizing
    0.46
     relativi
    0.45
     vain
    0.44
     relevant
    0.44
    ("",
    0.43
     cooperating
    0.43
     $
    0.43
    Activations Density 0.000%

    No Known Activations