© 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. 73419
    Prev
    Next
    INDEX
    Explanations

    drill bits, strings, fluids, rig

    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
     {
    -2.81
     \
    -2.38
    ik
    -2.34
    又は
    -2.33
    actéristi
    -2.25
     einigen
    -2.25
    el
    -2.23
    /
    -2.23
     Frequently
    -2.23
    ou
    -2.22
    POSITIVE LOGITS
     itſelf
    2.59
     sebaik
    2.33
    likace
    2.16
    龃
    2.08
     intentó
    2.06
     houver
    2.03
    .
    2.02
     adanya
    2.00
     exercí
    1.99
    ⤵
    1.98
    Activations Density 0.011%

    No Known Activations