© 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. 156478
    Prev
    Next
    INDEX
    Explanations

    pre-order / alternative / affairs

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

    Ethereum staking

    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
    行
    0.53
    入
    0.48
    疑問
    0.47
    형
    0.47
    今日
    0.46
    生
    0.46
    ROCK
    0.46
    ジネス
    0.46
    Singer
    0.46
    出
    0.45
    POSITIVE LOGITS
     mudanças
    0.51
     mudança
    0.50
     migraines
    0.49
     grips
    0.48
     করিয়ে
    0.46
     rejuvenated
    0.46
     boosters
    0.45
     ilaç
    0.45
     hiccups
    0.43
    Checks
    0.43
    Activations Density 0.001%

    No Known Activations