© 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. 155351
    Prev
    Next
    INDEX
    Explanations

    people and things

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

    information gathering and question answering

    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
     dưới
    0.48
    MONGO
    0.46
    iembre
    0.45
     alternativas
    0.44
    olutions
    0.43
    郗
    0.43
    帳に追加
    0.43
    लेक्ट
    0.42
    购买
    0.42
     URANIUM
    0.42
    POSITIVE LOGITS
    ܗ
    0.53
     district
    0.45
     크게
    0.45
     nást
    0.44
     life
    0.44
     ка
    0.44
    a
    0.44
     nota
    0.43
     charismatic
    0.43
     Skype
    0.43
    Activations Density 0.000%

    No Known Activations