© 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. 210588
    Prev
    Next
    INDEX
    Explanations

    expressing gratitude

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

    life, genre, or inherent disputes

    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
    𝕚
    0.54
     territoriale
    0.51
     bonito
    0.51
     magn
    0.49
     isometric
    0.49
    anim
    0.48
     deluge
    0.48
    ANIM
    0.47
    runoff
    0.47
    マグ
    0.47
    POSITIVE LOGITS
    销售
    0.46
    懋
    0.45
    លោក
    0.42
     ойноо
    0.41
    旅游
    0.40
    业协会
    0.40
     Epoch
    0.40
    สำ
    0.40
    ཟ
    0.40
     Event
    0.39
    Activations Density 0.003%

    No Known Activations