© 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. 33930
    Prev
    Next
    INDEX
    Explanations

    plans and planning

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

    making a plan

    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
    c
    1.04
    as
    0.91
    at
    0.89
    ة
    0.84
    v
    0.80
    be
    0.78
    b
    0.74
    t
    0.73
    al
    0.72
    ther
    0.72
    POSITIVE LOGITS
     plans
    1.20
     planification
    1.11
     Plans
    1.04
     PLANS
    1.04
     planen
    1.04
     планы
    1.04
    plans
    1.02
     плана
    1.01
     плани
    1.00
    計劃
    1.00
    Activations Density 0.066%

    No Known Activations