© 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. 3725
    Prev
    Next
    INDEX
    Explanations

    Converting numbers, empires, fear

    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
    损
    0.55
    四个
    0.49
     hvert
    0.49
     Coins
    0.47
    每个
    0.47
     вироб
    0.47
    诊
    0.47
    各个
    0.46
     každ
    0.45
     Fitbit
    0.45
    POSITIVE LOGITS
     gravity
    0.56
     calculus
    0.52
     populous
    0.49
    ז
    0.45
     evil
    0.44
    iyy
    0.44
     prototypical
    0.44
    acles
    0.44
    intersects
    0.43
    न
    0.43
    Activations Density 0.000%

    No Known Activations