© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129698
    Prev
    Next
    INDEX
    Explanations

    academic citations and references seem to be enclosed in brackets or parentheses and followed by punctuation.references and citationsbracketed references

    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
    -1.09
     Field
    -1.07
    lyon
    -1.05
     for
    -1.04
     For
    -1.02
     Students
    -1.01
     Methods
    -1.00
    D
    -1.00
     उत्तर
    -1.00
    ときは
    -0.99
    POSITIVE LOGITS
    donde
    1.45
    Recept
    1.28
    Kako
    1.27
    んじゃ
    1.26
    もありました
    1.26
    Profes
    1.20
    <bos>
    1.20
    Dij
    1.20
    Terima
    1.16
    ですが
    1.15
    Activations Density 0.001%

    No Known Activations