© 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. 200473
    Prev
    Next
    INDEX
    Explanations

    crisis, clue, rally, presidential, box

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

    sensitive matters and difficulties

    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
     saluran
    0.45
     accept
    0.44
     facets
    0.43
     assis
    0.43
     deliver
    0.42
     strengthen
    0.42
    护
    0.42
    สาน
    0.41
     conduite
    0.41
     aspects
    0.41
    POSITIVE LOGITS
    ADER
    0.49
    iko
    0.46
     BOARD
    0.46
     জন্য
    0.45
    ön
    0.44
    ilo
    0.44
    adá
    0.44
    ռ
    0.44
    ber
    0.43
    ía
    0.43
    Activations Density 0.000%

    No Known Activations