© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9862
    Prev
    Next
    INDEX
    Explanations

    6 see hell

    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
    n
    0.58
    on
    0.50
    s
    0.47
    bing
    0.45
    b
    0.44
     Bow
    0.43
    ed
    0.43
    ion
    0.43
    patch
    0.43
    p
    0.43
    POSITIVE LOGITS
    Jogador
    0.50
    Stabilise
    0.46
    Creat
    0.45
    Czas
    0.45
    を行い
    0.44
    ᕈ
    0.44
    ওয়
    0.43
    Gem
    0.43
     litres
    0.43
     utilising
    0.43
    Activations Density 0.009%

    No Known Activations