© 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. 107695
    Prev
    Next
    INDEX
    Explanations

    pm or am time qualifiers

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

    system, institutional, or systemic concepts

    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
    怯
    0.50
    सात
    0.48
     не
    0.48
    SEPT
    0.47
    是一款
    0.46
    Nicht
    0.46
    NERVE
    0.45
    不仅仅
    0.45
    ﾂ
    0.44
    SHIP
    0.43
    POSITIVE LOGITS
     läht
    0.51
     ID
    0.49
     informado
    0.49
     Vegeta
    0.48
     Bain
    0.46
     Palma
    0.46
     Id
    0.45
     IDs
    0.45
    lbrack
    0.45
     Algar
    0.45
    Activations Density 0.001%

    No Known Activations