© 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. 65517
    Prev
    Next
    INDEX
    Explanations

    who they are

    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
    焼く
    -0.85
    érité
    -0.75
     робота
    -0.74
     mở
    -0.72
     rowspan
    -0.72
    roch
    -0.72
    टक
    -0.72
    raciones
    -0.71
    примеча
    -0.70
    );}
    -0.70
    POSITIVE LOGITS
     person
    2.28
     PERSON
    1.65
     pessoa
    1.63
    person
    1.57
     human
    1.53
     individuals
    1.48
     человека
    1.44
     Person
    1.43
     человек
    1.43
    Person
    1.41
    Activations Density 0.022%

    No Known Activations