© 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. 105900
    Prev
    Next
    INDEX
    Explanations

    verbs followed by objects/locations

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

    states and observations

    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
     NAC
    0.49
     সম্ভবত
    0.47
    साठी
    0.46
     核
    0.46
     FIRST
    0.46
     SECURITY
    0.45
     TRO
    0.45
     แจ
    0.45
     送料無料
    0.45
    6
    0.45
    POSITIVE LOGITS
     erreurs
    0.55
    ovalo
    0.44
     образовањем
    0.43
    mentation
    0.43
     revelations
    0.41
    stances
    0.41
    lications
    0.39
    elajaran
    0.39
     scheming
    0.39
     advertis
    0.39
    Activations Density 0.001%

    No Known Activations