© 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. 138067
    Prev
    Next
    INDEX
    Explanations

    DNR, IRS, scar, health

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

    summarizing youtube videos and articles

    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
    wy
    0.54
    ou
    0.52
    ίλ
    0.47
     underway
    0.46
     hacking
    0.45
    ν
    0.45
    ță
    0.45
    મ
    0.44
    א
    0.44
    ulls
    0.44
    POSITIVE LOGITS
     tratado
    0.51
     ligero
    0.49
     conocimientos
    0.49
     informazioni
    0.49
     creado
    0.49
     作
    0.47
     comentario
    0.47
     Brush
    0.47
     Prés
    0.46
     conocimiento
    0.46
    Activations Density 0.001%

    No Known Activations