© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4409
    Prev
    Next
    INDEX
    Explanations

    multilingual content

    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_34/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
    ができます
    -0.98
    Şi
    -0.97
     disini
    -0.94
     jeugd
    -0.94
    اين
    -0.93
     Еще
    -0.91
    ためには
    -0.91
    際に
    -0.90
    んですけど
    -0.89
    きち
    -0.89
    POSITIVE LOGITS
    ،
    0.99
     ،
    0.94
     менять
    0.91
    ínu
    0.91
    <bos>
    0.91
     ו
    0.90
    olving
    0.89
    hever
    0.87
    や
    0.86
     zob
    0.85
    Activations Density 0.001%

    No Known Activations