© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6966
    Prev
    Next
    INDEX
    Explanations

    probability formulas and text formatting

    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
     that
    -1.57
     this
    -1.46
     komment
    -1.26
     Each
    -1.25
     if
    -1.19
     There
    -1.17
    Each
    -1.16
     Although
    -1.16
     When
    -1.15
     However
    -1.13
    POSITIVE LOGITS
     wonderfully
    1.28
     peculi
    1.20
     hugely
    1.16
     delightfully
    1.16
     Czechos
    1.16
     cresc
    1.15
     Simult
    1.15
     récemment
    1.13
     repug
    1.12
     sacerd
    1.10
    Activations Density 0.008%

    No Known Activations