© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3641
    Prev
    Next
    INDEX
    Explanations

    tables and comparisons

    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_7_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
    ಿ
    2.75
    みると
    2.75
    いく
    2.63
    いますが
    2.58
    みた
    2.52
    ্মান
    2.49
    慓
    2.41
     ultrast
    2.34
    ebab
    2.32
    いる
    2.31
    POSITIVE LOGITS
    ntz
    2.87
    чью
    2.42
    ન
    2.32
    ếu
    2.27
    𝐲
    2.25
    콥
    2.24
    ặng
    2.24
    𝐨
    2.22
    飫
    2.19
    AuthState
    2.19
    Activations Density 0.055%

    No Known Activations