© 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. 72666
    Prev
    Next
    INDEX
    Explanations

    research papers and their findings

    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
     and
    -1.48
     that
    -1.24
     signifikan
    -1.23
     BioLib
    -1.13
    PENDAHULUAN
    -1.09
     penghargaan
    -1.09
     terkenal
    -1.09
    osoba
    -1.09
    )}
    -1.07
    (!__
    -1.07
    POSITIVE LOGITS
     also
    1.98
    i
    1.26
    จึง
    1.24
     praça
    1.19
     focuses
    1.18
     further
    1.17
    aville
    1.14
     is
    1.14
    大丈夫です
    1.13
     altres
    1.13
    Activations Density 0.102%

    No Known Activations