© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5779
    Prev
    Next
    INDEX
    Explanations

    Gemma model identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    どちら
    1.30
    だから
    1.28
    ミ
    1.26
    とても
    1.25
    水の
    1.24
    なので
    1.23
    たい
    1.22
    マイ
    1.21
    などの
    1.19
    同じ
    1.18
    POSITIVE LOGITS
     Κο
    1.13
     scandal
    1.12
     λ
    1.10
     landed
    1.09
     marched
    1.07
    fia
    1.07
     grabbed
    1.07
     Χ
    1.04
     pulled
    1.02
     σ
    1.02
    Activations Density 0.115%

    No Known Activations