© 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. 68232
    Prev
    Next
    INDEX
    Explanations

    lack of availability or success

    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
    Voir
    -0.89
    Different
    -0.88
    czna
    -0.87
     Redewendung
    -0.86
     these
    -0.86
    noinspection
    -0.84
    由
    -0.84
    Beberapa
    -0.84
    cry
    -0.82
    different
    -0.81
    POSITIVE LOGITS
     unable
    1.55
     unavailable
    1.36
     cannot
    1.36
    找不到
    1.16
     incapable
    1.14
    无法
    1.11
     невозможно
    1.09
     không
    1.05
     inability
    1.04
    だけでは
    1.04
    Activations Density 0.167%

    No Known Activations