© 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. 117191
    Prev
    Next
    INDEX
    Explanations

    business specializes

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

    reading & specific continuations

    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
    ament
    0.43
    DLC
    0.42
     Norse
    0.42
     Updating
    0.41
     درمیان
    0.40
     Emulator
    0.40
    🥔
    0.40
     Specification
    0.40
    DX
    0.39
     Alamos
    0.39
    POSITIVE LOGITS
     conquista
    0.50
     vestido
    0.49
     ජී
    0.49
     沒有
    0.48
     ataque
    0.47
    黨
    0.47
     ਜਾ
    0.47
     吃
    0.47
     單
    0.47
     zag
    0.47
    Activations Density 0.000%

    No Known Activations