© 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. 152103
    Prev
    Next
    INDEX
    Explanations

    family history, communicators, wire

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

    Daily Scrum, save for, loved to

    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
    fung
    0.57
    Მ
    0.52
    latt
    0.47
    ambilan
    0.47
    approval
    0.46
    Კ
    0.46
    issati
    0.46
    filtr
    0.46
    Ნ
    0.46
    ्योपै
    0.45
    POSITIVE LOGITS
     amortization
    0.51
     congé
    0.47
    െ
    0.46
     African
    0.46
     Carolina
    0.46
     “
    0.45
     Montague
    0.44
     unsustainable
    0.44
     페
    0.43
     behold
    0.43
    Activations Density 0.000%

    No Known Activations