© 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. 71606
    Prev
    Next
    INDEX
    Explanations

    numbers in sequences

    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
     of
    -1.13
    <!--<
    -0.88
    FilterChain
    -0.85
    technologies
    -0.84
    valy
    -0.82
     shout
    -0.82
     фаса
    -0.80
    sprintf
    -0.79
     almost
    -0.79
    ченным
    -0.79
    POSITIVE LOGITS
    Referințe
    0.85
     克
    0.85
    這裡
    0.85
    Karina
    0.84
    三個
    0.84
    三种
    0.82
    akov
    0.80
     ACCESS
    0.79
     畳
    0.79
     Posteriormente
    0.79
    Activations Density 0.020%

    No Known Activations