© 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. 175922
    Prev
    Next
    INDEX
    Explanations

    finding new technology or products

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

    participles and headlines

    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
     understated
    0.47
     unapolog
    0.47
     prominently
    0.46
    patri
    0.45
     seeks
    0.45
     creativity
    0.45
    遇
    0.45
     undeniable
    0.45
    zens
    0.45
    is
    0.44
    POSITIVE LOGITS
    嬠
    0.48
    🤬
    0.47
    を使って
    0.46
    辂
    0.45
     মিনিটে
    0.45
    😲
    0.44
    眹
    0.44
    电视
    0.44
     między
    0.43
    矵
    0.43
    Activations Density 0.000%

    No Known Activations