© 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-65K
    7. 30869
    Prev
    Next
    INDEX
    Explanations

    GTA V air atmosphere

    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_65k_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
    orod
    0.48
    ጠና
    0.43
    institutional
    0.43
    mesini
    0.41
    였
    0.40
     στη
    0.40
    na
    0.39
    miştir
    0.39
    ljeni
    0.39
    irst
    0.38
    POSITIVE LOGITS
     contemplates
    0.47
     slags
    0.45
     forbids
    0.44
     Normalmente
    0.43
    وفة
    0.42
     contemplating
    0.42
     differentiates
    0.42
     ZDF
    0.41
    ﾛ
    0.41
     partake
    0.41
    Activations Density 0.005%

    No Known Activations