© 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. 3970
    Prev
    Next
    INDEX
    Explanations

    transitioning to a new state

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

    preparation for input

    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
    ANCES
    0.54
     שנים
    0.52
    ז
    0.52
     많은
    0.50
    兹
    0.50
    趼
    0.50
    כ
    0.47
    ༣
    0.47
    Nodo
    0.47
     ennemis
    0.46
    POSITIVE LOGITS
     initial
    0.67
     Initial
    0.64
    initial
    0.59
     transitioned
    0.59
     transitioning
    0.57
     during
    0.55
    Initial
    0.55
    transition
    0.55
     dehydrated
    0.54
    初始
    0.54
    Activations Density 0.011%

    No Known Activations