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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30491
    Prev
    Next
    INDEX
    Explanations

    property services and costs

    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
     rentals
    -0.82
    olá
    -0.81
    ädie
    -0.80
    ఓ
    -0.78
    :'',
    -0.78
     rental
    -0.78
     naše
    -0.78
     slovens
    -0.76
    Rental
    -0.75
    憲
    -0.75
    POSITIVE LOGITS
     trash
    1.53
     garbage
    1.41
     Trash
    1.37
     Garbage
    1.12
    garbage
    1.11
    trash
    1.10
     pest
    1.04
     lawn
    1.02
     rubbish
    0.98
    Trash
    0.98
    Activations Density 0.005%

    No Known Activations