© 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. 149680
    Prev
    Next
    INDEX
    Explanations

    semiconductor memory, online learning, single remote

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

    project context

    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
     bền
    0.56
     definido
    0.54
    ᱓
    0.54
     phức
    0.53
     transformação
    0.53
    𝒆
    0.53
     abraz
    0.52
    𝒊
    0.52
    ési
    0.51
    más
    0.51
    POSITIVE LOGITS
    Authority
    0.51
    ERT
    0.49
    loyd
    0.47
    EL
    0.47
    IS
    0.46
    kin
    0.45
    EK
    0.44
    IOD
    0.43
    0
    0.43
     subordinate
    0.43
    Activations Density 0.001%

    No Known Activations