© 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. 80023
    Prev
    Next
    INDEX
    Explanations

    gallery in relation to

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

    Azure confidentiality and services

    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
    Snackbar
    0.45
    Ether
    0.45
    వంటి
    0.43
    蒽
    0.42
    ConfigFiles
    0.42
    Marc
    0.42
     ethers
    0.41
    Updated
    0.40
     refreshed
    0.40
     نہ
    0.40
    POSITIVE LOGITS
    悖
    0.48
     বলেছিল
    0.47
    argue
    0.45
    ﺩ
    0.45
     বলেছে
    0.45
    icherheit
    0.45
    émie
    0.45
    生態
    0.45
     বলেছেন
    0.45
    ே
    0.45
    Activations Density 0.001%

    No Known Activations