© 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. 75231
    Prev
    Next
    INDEX
    Explanations

    internal latent space

    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
    m
    0.54
     Bally
    0.45
     premat
    0.45
     Cort
    0.44
    c
    0.43
    gmail
    0.41
    મિક
    0.40
    カ
    0.40
    sh
    0.40
     Bast
    0.40
    POSITIVE LOGITS
    кульп
    0.52
     రాజ్యం
    0.49
     స్వ
    0.48
     справедливо
    0.48
     структура
    0.47
     поли
    0.47
     же
    0.47
     గుర్త
    0.46
    龋
    0.46
     இணைப்பு
    0.46
    Activations Density 0.002%

    No Known Activations