© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84306
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

    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
     positivos
    -1.24
     så
    -1.19
     aisladas
    -1.12
     negativas
    -1.10
    There
    -1.08
     vivir
    -1.08
     resistir
    -1.05
    Depending
    -1.03
    ્ય
    -1.02
    前言
    -1.02
    POSITIVE LOGITS
     of
    2.88
     and
    1.63
     on
    1.14
     poiché
    1.13
     for
    1.05
    セラ
    1.05
    ledad
    1.05
     maaaring
    1.05
     also
    1.00
     ngan
    0.99
    Activations Density 0.042%

    No Known Activations