© 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. 201706
    Prev
    Next
    INDEX
    Explanations

    sequence of events

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

    then followed by an action

    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
    in
    0.64
    ä
    0.58
    us
    0.58
    át
    0.58
    ado
    0.57
    är
    0.56
    .…
    0.55
    ě
    0.54
     niemand
    0.53
    asn
    0.53
    POSITIVE LOGITS
     therefore
    0.61
    ますが
    0.61
     HOWEVER
    0.55
     λοι
    0.55
     ensues
    0.53
     Somit
    0.52
    selves
    0.52
     Поэтому
    0.51
    टामिन
    0.51
    いましたが
    0.50
    Activations Density 0.039%

    No Known Activations