© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100575
    Prev
    Next
    INDEX
    Explanations

    cold surfaces, roots warm

    np_acts-logits-general · gemini-2.5-flash-lite

    legitimate businesses and legal matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    io
    0.61
    icarbon
    0.48
    ס
    0.48
    aw
    0.47
    ound
    0.46
    constructor
    0.45
    amas
    0.44
    ajos
    0.44
    D
    0.44
    ih
    0.43
    POSITIVE LOGITS
     artistique
    0.50
     underside
    0.50
     εισ
    0.50
     constituer
    0.49
     splendor
    0.48
     manière
    0.47
     도시
    0.47
     acque
    0.46
     cinquième
    0.46
     oraș
    0.46
    Activations Density 0.001%

    No Known Activations