© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26818
    Prev
    Next
    INDEX
    Explanations

    this followed by time

    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_22/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
     to
    -1.82
     of
    -1.73
    つまり
    -1.55
    が
    -1.53
    を
    -1.49
     now
    -1.42
    そして
    -1.42
    などを
    -1.37
    性質
    -1.34
    hermoso
    -1.30
    POSITIVE LOGITS
    為に
    1.81
    corrhi
    1.79
    様に
    1.74
    久し
    1.53
    様な
    1.52
    こともあり
    1.52
    ようになります
    1.50
    感じで
    1.46
    の絵
    1.45
    おそ
    1.45
    Activations Density 0.022%

    No Known Activations