© 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. 33542
    Prev
    Next
    INDEX
    Explanations

    in fact, followed by elaboration

    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
     not
    -1.45
     также
    -1.31
     azonban
    -1.24
     również
    -1.20
     imidlertid
    -1.19
     також
    -1.18
     kuitenkin
    -1.18
     không
    -1.17
     però
    -1.13
     également
    -1.12
    POSITIVE LOGITS
    むしろ
    1.59
     наоборот
    1.39
     sogar
    1.34
    反而
    1.26
     it
    1.15
    tambah
    1.12
     anzi
    1.09
     actually
    1.07
     diría
    1.05
     malah
    1.00
    Activations Density 0.017%

    No Known Activations