© 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. 10-GEMMASCOPE-RES-131K
    7. 86137
    Prev
    Next
    INDEX
    Explanations

    economic cost

    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_10/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
     peluche
    -1.37
     bestia
    -1.36
     toppen
    -1.34
     assise
    -1.34
     Biblia
    -1.32
     Amerika
    -1.32
     brosse
    -1.32
     beso
    -1.30
    ！(
    -1.28
    isierte
    -1.27
    POSITIVE LOGITS
     including
    1.55
     of
    1.44
     cost
    1.26
     such
    1.24
     involving
    1.22
     include
    1.18
    =[];
    1.16
    oznam
    1.14
     또는
    1.13
     with
    1.13
    Activations Density 0.025%

    No Known Activations