© 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. 251055
    Prev
    Next
    INDEX
    Explanations

    writing and punctuation

    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
    겠지만
    0.45
    었는데
    0.45
    苇
    0.44
     whack
    0.43
    胫
    0.43
     Pharisees
    0.41
    鸵
    0.41
    োধ
    0.40
     whatever
    0.40
     kangaroo
    0.40
    POSITIVE LOGITS
    FILE
    0.50
    )=
    0.49
     پڑھ
    0.48
     novembre
    0.47
     Honduras
    0.46
    INDIA
    0.46
     INDIA
    0.45
    }{
    0.45
     जिल्ह
    0.45
     iStock
    0.45
    Activations Density 0.001%

    No Known Activations