© 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. 69461
    Prev
    Next
    INDEX
    Explanations

    baking, money, suicide, imagine

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

    balance and relationship dynamics

    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
    ме
    0.51
    otá
    0.50
    декс
    0.50
    PosX
    0.49
    케이
    0.48
    엑
    0.47
    ಮ
    0.47
    압
    0.47
     회사
    0.46
     excerpts
    0.46
    POSITIVE LOGITS
     GameObject
    0.53
     परंतु
    0.49
     n
    0.48
     cathedral
    0.46
    idin
    0.46
     suicide
    0.45
    ठी
    0.44
     charitable
    0.44
    icin
    0.44
     Election
    0.43
    Activations Density 0.001%

    No Known Activations