© 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. 83082
    Prev
    Next
    INDEX
    Explanations

    not alone

    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
    Printf
    -0.96
    eltjes
    -0.91
    iterraneo
    -0.89
     ktorí
    -0.85
    mayr
    -0.85
    andan
    -0.83
    getString
    -0.83
     Agu
    -0.82
     Straus
    -0.79
    divia
    -0.78
    POSITIVE LOGITS
     alone
    8.13
    alone
    5.81
     Alone
    5.41
    Alone
    5.13
     ALONE
    4.75
     solo
    4.66
     alleine
    4.53
     allein
    4.13
     sozinho
    3.80
    solo
    3.66
    Activations Density 0.141%

    No Known Activations