© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104420
    Prev
    Next
    INDEX
    Explanations

    describing actions or states after a word

    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
     almeno
    -1.17
     حتی
    -0.96
     pangan
    -0.95
     étan
    -0.95
     réfrig
    -0.94
     seny
    -0.94
     rami
    -0.93
     equally
    -0.92
     redé
    -0.90
    と言える
    -0.90
    POSITIVE LOGITS
     blanket
    1.08
     or
    1.06
     with
    0.98
    }}_
    0.98
    (!_
    0.97
    xun
    0.96
    []{"
    0.95
     this
    0.94
     creates
    0.94
     created
    0.94
    Activations Density 0.007%

    No Known Activations