© 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. 139076
    Prev
    Next
    INDEX
    Explanations

    sometimes improvements merchant analogy surprising

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

    automating manual processes

    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
    োই
    0.46
     REACTOR
    0.44
    uridad
    0.43
    ('@
    0.43
    鼓励
    0.43
    的确
    0.43
    loé
    0.43
    炅
    0.43
     Episodes
    0.43
     Knitting
    0.43
    POSITIVE LOGITS
    datal
    0.50
    v
    0.49
    me
    0.49
    jav
    0.47
    석
    0.47
    southern
    0.46
    CMD
    0.46
    lashes
    0.45
    zon
    0.44
    hands
    0.44
    Activations Density 0.001%

    No Known Activations