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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11501
    Prev
    Next
    INDEX
    Explanations

    quantifiers and specifications

    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
     Insects
    -0.93
     alltså
    -0.90
     serangga
    -0.90
     εισ
    -0.86
    Lina
    -0.85
     emberek
    -0.85
     inexorable
    -0.84
    Хотя
    -0.84
     progenitor
    -0.83
     التي
    -0.83
    POSITIVE LOGITS
     isso
    1.08
    even
    0.96
    BitConverter
    0.92
     ug
    0.91
     foran
    0.90
     Proceedings
    0.90
    ⁸
    0.90
     عاشقانه
    0.86
     is
    0.85
    eight
    0.85
    Activations Density 0.183%

    No Known Activations