© 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. 62468
    Prev
    Next
    INDEX
    Explanations

    navigating threads

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

    emotional and genetic consequences

    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
     consult
    0.51
    ¿
    0.51
    Ս
    0.45
    К
    0.44
    Б
    0.42
    util
    0.41
    require
    0.41
     d
    0.41
     whereas
    0.41
     consulted
    0.41
    POSITIVE LOGITS
     итоге
    0.57
     Omphalodes
    0.56
     adhipp
    0.53
     gevoel
    0.53
     තුළ
    0.53
    чним
    0.50
     TRANSPORTURI
    0.47
     感じ
    0.47
     సమస్య
    0.46
     sentidos
    0.46
    Activations Density 0.000%

    No Known Activations