© 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-262K
    7. 91609
    Prev
    Next
    INDEX
    Explanations

    GitHub README

    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
     måste
    0.45
    ovariant
    0.45
    ammonium
    0.42
     dobbiamo
    0.42
     kojoj
    0.42
    𝙎
    0.41
     ovako
    0.41
    SAA
    0.40
    registrar
    0.40
    𝗙
    0.40
    POSITIVE LOGITS
     GitHub
    0.71
     README
    0.64
     github
    0.63
     readme
    0.59
    README
    0.58
    GitHub
    0.58
     Github
    0.57
    github
    0.56
    Readme
    0.56
    readme
    0.52
    Activations Density 0.105%

    No Known Activations