© 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. 168751
    Prev
    Next
    INDEX
    Explanations

    special words after common ones

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

    booking in advance

    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
    AndroidResource
    0.50
    oger
    0.46
    ွေ
    0.43
    centroid
    0.42
    دع
    0.41
    춧
    0.41
    imread
    0.41
     চলচ্
    0.40
    at
    0.40
     écriv
    0.38
    POSITIVE LOGITS
    dp
    0.50
     Groupe
    0.47
     squares
    0.45
     machines
    0.45
     is
    0.45
    gruppe
    0.45
     Ủy
    0.45
     operators
    0.44
     categorie
    0.44
    两
    0.44
    Activations Density 0.001%

    No Known Activations