© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34828
    Prev
    Next
    INDEX
    Explanations

    organizations and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     墙
    -1.11
    .‏
    -1.07
    ὸν
    -1.01
    不僅
    -0.99
    我现在
    -0.98
    langsung
    -0.98
    不仅
    -0.98
    cteur
    -0.96
     навіть
    -0.95
    尔夫
    -0.95
    POSITIVE LOGITS
     and
    1.23
     estimate
    1.04
    を失
    1.02
     policy
    1.01
     strategy
    0.99
    齟
    0.98
    が悪い
    0.98
     Sør
    0.96
     estimates
    0.95
     goal
    0.94
    Activations Density 0.052%

    No Known Activations