© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76756
    Prev
    Next
    INDEX
    Explanations

    word endings or continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    を
    -1.99
    が
    -1.90
    でしょうね
    -1.64
    つまり
    -1.63
    は
    -1.52
    があります
    -1.50
    も
    -1.49
    で
    -1.46
    方針
    -1.45
    そして
    -1.43
    POSITIVE LOGITS
    為に
    2.11
    んですね
    1.75
    際には
    1.64
    olge
    1.59
    ところに
    1.57
    えっ
    1.55
    んじゃない
    1.53
    際は
    1.52
    こともあり
    1.50
    んですよね
    1.49
    Activations Density 0.121%

    No Known Activations