© 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. 201898
    Prev
    Next
    INDEX
    Explanations

    rolls ofsubsidy rollsenvelope expiry

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

    fatigue and tiredness

    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
     τη
    0.46
     Tauri
    0.46
    𝔻
    0.45
    ন
    0.45
     ß
    0.44
    σκ
    0.44
     kelahiran
    0.44
     که
    0.44
    อย่าง
    0.44
     forks
    0.44
    POSITIVE LOGITS
    Expiry
    0.49
    赅
    0.48
    вете
    0.45
    Envelope
    0.44
     कार्यकारिणी
    0.43
    Cancel
    0.43
     المراجعه
    0.42
    рока
    0.42
    Range
    0.42
    Bank
    0.42
    Activations Density 0.000%

    No Known Activations