© 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. 26703
    Prev
    Next
    INDEX
    Explanations

    state or descriptor

    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
     also
    -1.60
     notwithstanding
    -1.23
    もあって
    -1.15
    それにしても
    -1.15
     now
    -1.14
     currently
    -1.13
    子は
    -1.11
    くれて
    -1.10
     already
    -1.09
     reagieren
    -1.09
    POSITIVE LOGITS
    にほんブログ村
    1.38
     able
    1.38
    ícias
    1.25
    ijų
    1.20
    /*++
    1.16
    昨日は
    1.13
     nejlepší
    1.08
     and
    1.07
     hígado
    1.05
    もうすぐ
    1.05
    Activations Density 0.077%

    No Known Activations