© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28411
    Prev
    Next
    INDEX
    Explanations

    GEN, Fe, is, Q -> GENOTYPIC, Feasibility, is needed, Q:

    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
    ▒
    -1.14
    МП
    -1.13
     coloré
    -1.13
     marins
    -1.09
    🏦
    -1.09
     sportif
    -1.09
    IZES
    -1.09
    РТ
    -1.08
    ?></
    -1.07
    ALAND
    -1.07
    POSITIVE LOGITS
    3
    1.07
     and
    1.06
     during
    1.00
     any
    0.98
    Acer
    0.96
     at
    0.93
     always
    0.92
    ↵↵
    0.90
     every
    0.90
    ↵
    0.90
    Activations Density 0.003%

    No Known Activations