© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 248530
    Prev
    Next
    INDEX
    Explanations

    social media links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     senator
    0.45
     video
    0.42
     provoke
    0.42
     senses
    0.41
     x
    0.40
     soc
    0.40
     sims
    0.39
    T
    0.39
     profiles
    0.38
     television
    0.38
    POSITIVE LOGITS
    ईआरटी
    0.51
    acidade
    0.43
     Aufbau
    0.42
     SCGS
    0.41
    ıcı
    0.41
    윰
    0.40
     중심
    0.40
    forter
    0.39
    чною
    0.39
     Bodrum
    0.39
    Activations Density 0.001%

    No Known Activations