© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203972
    Prev
    Next
    INDEX
    Explanations

    Aglio e Olio, Voice, VIP, VS Code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     доме
    0.61
     expériences
    0.53
    獃
    0.52
     микро
    0.51
     развитии
    0.51
    държа
    0.50
     музе
    0.48
    皘
    0.48
     свобо
    0.48
    ărul
    0.48
    POSITIVE LOGITS
     Not
    0.50
     int
    0.48
     Int
    0.48
     Raises
    0.47
    e
    0.47
     +/-
    0.46
     not
    0.45
     "'"
    0.45
     when
    0.44
     Prote
    0.44
    Activations Density 0.003%

    No Known Activations