© 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. 160336
    Prev
    Next
    INDEX
    Explanations

    ground floor units

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

    describing locations and relative positions

    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
     şehr
    0.46
    ᱑
    0.45
    宿泊
    0.44
    AREA
    0.44
    FIT
    0.43
     શહે
    0.42
    Designed
    0.42
     conçu
    0.42
     området
    0.42
     මිල
    0.42
    POSITIVE LOGITS
     വിഷ
    0.45
     ■
    0.44
     blink
    0.43
     FontWeight
    0.41
     Aids
    0.41
     Ribeiro
    0.41
    bnr
    0.41
     HIV
    0.41
     Indians
    0.40
     Archive
    0.40
    Activations Density 0.036%

    No Known Activations