© 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. 45561
    Prev
    Next
    INDEX
    Explanations

    fibre extensions, home security, accommodation

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

    linking words or phrases

    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
    Branch
    0.47
     وسي
    0.47
    Flow
    0.46
     ولي
    0.45
    Programme
    0.45
    Scha
    0.44
     trimmer
    0.44
     Φ
    0.43
    せん
    0.43
     ገን
    0.42
    POSITIVE LOGITS
    anggilan
    0.48
    ably
    0.47
    udio
    0.47
    tsó
    0.45
     bỏ
    0.44
     เรียก
    0.44
    นี่
    0.44
    手游
    0.44
    incident
    0.44
    tons
    0.43
    Activations Density 0.001%

    No Known Activations