© 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. 10649
    Prev
    Next
    INDEX
    Explanations

    with spacing

    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
    ه
    0.45
     отношения
    0.44
     gruppi
    0.44
     allgeme
    0.44
    pot
    0.41
    jenigen
    0.41
     healing
    0.41
     walang
    0.41
    king
    0.41
    healing
    0.40
    POSITIVE LOGITS
    виде
    0.46
    ωσ
    0.46
    놉
    0.45
    鳍
    0.44
     readout
    0.43
    afat
    0.43
    導入
    0.43
    اول
    0.43
    можно
    0.42
    álu
    0.42
    Activations Density 0.031%

    No Known Activations