© 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. 193267
    Prev
    Next
    INDEX
    Explanations

    holiday observances

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

    original rhyme

    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
    ’
    0.52
    SA
    0.45
    MSO
    0.43
    there
    0.43
    miner
    0.43
     rig
    0.42
    НИЕ
    0.42
    s
    0.42
     provident
    0.42
    SB
    0.41
    POSITIVE LOGITS
    າ
    0.57
     एंगल
    0.52
    घटना
    0.49
     вари
    0.49
     інші
    0.48
    ກ
    0.48
    𝒖
    0.48
    埓
    0.48
    ⓪
    0.48
    ellingen
    0.47
    Activations Density 0.000%

    No Known Activations