© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14234
    Prev
    Next
    INDEX
    Explanations

    is the, be the, better the

    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_16k_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
     unor
    0.68
     unei
    0.65
     unui
    0.63
     czego
    0.60
     suatu
    0.55
     อะไร
    0.54
     innego
    0.52
    <unused2148>
    0.52
     anderem
    0.50
     innym
    0.50
    POSITIVE LOGITS
     the
    2.02
    the
    1.92
    The
    1.59
     The
    1.28
     את
    1.10
    sthe
    1.10
     ihe
    1.03
    THE
    1.01
     THE
    1.00
     teh
    0.99
    Activations Density 1.146%

    No Known Activations