© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9922
    Prev
    Next
    INDEX
    Explanations

    relative positions and proximity

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

    nearby locations and relationships

    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_40_width_16k_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
    ule
    0.42
     widest
    0.40
    zigen
    0.37
    ita
    0.37
    зня
    0.36
     സാധാരണ
    0.36
    凡
    0.36
     prostředí
    0.36
     candid
    0.35
    bz
    0.34
    POSITIVE LOGITS
     nearby
    2.75
    nearby
    2.47
    Nearby
    2.34
     Nearby
    2.25
     neighboring
    2.20
     neighbouring
    2.09
     adjacent
    2.03
     сосед
    1.89
    隣
    1.83
     adjoining
    1.77
    Activations Density 0.487%

    No Known Activations