© 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. 28217
    Prev
    Next
    INDEX
    Explanations

    code components and framework names

    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
     and
    -2.03
     this
    -1.92
     more
    -1.63
     all
    -1.50
     with
    -1.49
     from
    -1.45
     when
    -1.45
     one
    -1.38
     or
    -1.37
     every
    -1.37
    POSITIVE LOGITS
     Jesucristo
    1.38
    ඍ
    1.29
     mehreren
    1.25
    كم
    1.22
     некото
    1.22
    ౮
    1.20
    л
    1.18
     angesehen
    1.18
     stärker
    1.17
     Unterschiede
    1.16
    Activations Density 0.004%

    No Known Activations