© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 201779
    Prev
    Next
    INDEX
    Explanations

    who cares

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

    explosive growth

    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
    穎
    0.49
     cương
    0.46
    ції
    0.44
     pregnancy
    0.43
     Pregnancy
    0.43
    тування
    0.43
    рю
    0.41
     النفس
    0.41
    🤰
    0.41
    лд
    0.40
    POSITIVE LOGITS
    nw
    0.56
    tnie
    0.52
    soccer
    0.51
    serif
    0.51
    segaretro
    0.51
    titulo
    0.50
    heroes
    0.50
    m
    0.50
    pessoas
    0.50
    rd
    0.50
    Activations Density 0.001%

    No Known Activations