© 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. 70620
    Prev
    Next
    INDEX
    Explanations

    html tags and attributes

    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
    -1.10
    境内
    -0.92
    xC
    -0.89
     mostr
    -0.85
    ilton
    -0.84
     achieve
    -0.84
     auf
    -0.83
    ufige
    -0.83
     adatt
    -0.83
    arikan
    -0.82
    POSITIVE LOGITS
    igth
    1.34
    ebly
    1.30
     suddenly
    1.23
    rsquo
    1.18
    hassee
    1.15
    mockMvc
    1.13
     europé
    1.12
     henvis
    1.10
    ograft
    1.10
     árvores
    1.09
    Activations Density 0.041%

    No Known Activations