© 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. 71558
    Prev
    Next
    INDEX
    Explanations

    introductory phrases or punctuation followed by elaboration

    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
    ologists
    -1.19
     gewöhnlich
    -1.16
     обычно
    -1.16
    всегда
    -1.16
     zelve
    -1.13
    さっき
    -1.13
    毫米
    -1.12
     realice
    -1.08
     biasanya
    -1.05
     fhall
    -1.05
    POSITIVE LOGITS
     I
    1.38
     reading
    1.11
     Grüße
    1.10
     this
    1.06
     my
    1.01
     especially
    0.96
     Theorie
    0.96
     жаль
    0.92
     яй
    0.91
     メニュー
    0.90
    Activations Density 0.021%

    No Known Activations