© 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. 68805
    Prev
    Next
    INDEX
    Explanations

    production and function

    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
     including
    -1.20
     several
    -1.13
     two
    -1.13
     both
    -1.09
     mostly
    -1.05
     three
    -1.05
     includes
    -1.03
     partially
    -1.02
     many
    -1.00
     every
    -0.97
    POSITIVE LOGITS
     قادر
    1.17
     capable
    1.09
    capable
    1.08
    用来
    1.08
     maniere
    1.07
    deliver
    1.05
     producing
    1.05
    produce
    1.05
     gainera
    1.02
     mampu
    1.01
    Activations Density 0.201%

    No Known Activations