© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 188728
    Prev
    Next
    INDEX
    Explanations

    specific concepts and their immediate context

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

    issues, commentaries, locations, rocky planets

    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
    υ
    0.47
    TRE
    0.47
     вя
    0.47
    ુ
    0.47
    ッキ
    0.45
    ਨ੍ਹਾਂ
    0.45
    …?
    0.45
     перехода
    0.45
    𓈒
    0.45
     deportivos
    0.44
    POSITIVE LOGITS
     estimates
    0.59
     ESTIM
    0.48
    荷兰
    0.47
     requirements
    0.45
     unaware
    0.45
    java
    0.45
     JavaVersion
    0.45
    咏
    0.45
     context
    0.43
    estimate
    0.42
    Activations Density 0.000%

    No Known Activations