© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72185
    Prev
    Next
    INDEX
    Explanations

    unique and descriptive phrases

    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
     or
    -1.46
    だったので
    -1.24
     and
    -1.19
     to
    -1.14
     four
    -1.13
     verschillen
    -1.12
     Before
    -1.12
     testSet
    -1.11
     aprilie
    -1.08
     který
    -1.07
    POSITIVE LOGITS
     these
    2.19
     this
    2.06
    these
    1.60
     of
    1.53
     each
    1.30
     visse
    1.23
    これらの
    1.19
     perpé
    1.17
    ここの
    1.16
     THESE
    1.15
    Activations Density 0.049%

    No Known Activations