© 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. 1853
    Prev
    Next
    INDEX
    Explanations

    enough der, along Old

    np_acts-logits-general · gemini-2.5-flash-lite

    Wimbledon, galaxy, Madagascar

    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
     makalah
    0.52
    +",
    0.50
    Sal
    0.48
    贰
    0.47
     nessuna
    0.47
    quiera
    0.44
    他說
    0.44
    ----------------
    0.43
     legitt
    0.43
    ================
    0.42
    POSITIVE LOGITS
    rein
    0.52
    ку
    0.51
    f
    0.49
     windmills
    0.49
     갤럭시
    0.48
    sampled
    0.47
     cyclists
    0.46
    vaccinated
    0.45
    icier
    0.45
     thatch
    0.45
    Activations Density 0.000%

    No Known Activations