© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14789
    Prev
    Next
    INDEX
    Explanations

    the followed by laws

    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
    再一次
    -1.50
     Empieza
    -1.34
     ďal
    -1.34
     alcuni
    -1.30
     alcune
    -1.27
     molti
    -1.25
     dalších
    -1.23
     delectable
    -1.23
     particolar
    -1.23
     nedost
    -1.23
    POSITIVE LOGITS
    ּוֹ
    1.45
     or
    1.41
    PasswordEncoder
    1.38
     before
    1.27
     on
    1.25
     three
    1.24
     five
    1.23
     but
    1.23
     Generally
    1.23
     eight
    1.22
    Activations Density 0.033%

    No Known Activations