© 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. 28427
    Prev
    Next
    INDEX
    Explanations

    fun activities and things

    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
     any
    -1.25
     similar
    -1.23
     much
    -1.13
    H
    -1.12
     pertinent
    -1.11
     substantial
    -1.09
     critical
    -1.08
    S
    -1.08
     a
    -1.06
     needed
    -1.06
    POSITIVE LOGITS
    และ
    1.28
    Tämä
    1.14
     geralmente
    1.13
    Ⴀ
    1.13
    Regie
    1.13
    captcha
    1.13
    OVERY
    1.12
    kalender
    1.11
    urez
    1.11
    Aquí
    1.11
    Activations Density 0.020%

    No Known Activations