© 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. 59239
    Prev
    Next
    INDEX
    Explanations

    the third

    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
     Secondly
    -1.07
     fünf
    -0.96
    ㈡
    -0.94
     пять
    -0.90
     primeiro
    -0.89
    ▏
    -0.88
    enciaga
    -0.87
     нескольких
    -0.83
    几个
    -0.83
     cinco
    -0.82
    POSITIVE LOGITS
     third
    8.13
    third
    6.09
    第三
    5.41
    Third
    5.19
     troisième
    4.66
     Thirdly
    4.66
     Third
    4.56
     tercera
    4.53
     THIRD
    4.44
    THIRD
    4.41
    Activations Density 0.118%

    No Known Activations