© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    why it's great

    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
    ;"+
    1.67
     ;
    1.59
    :'.
    1.55
    ';"+
    1.54
     ”.
    1.53
    ।...
    1.52
    ।
    1.51
    ';",
    1.51
    ।''
    1.50
    ,:
    1.50
    POSITIVE LOGITS
    ちょっと
    1.15
    とりあえず
    1.11
    ここ
    1.11
    や
    1.07
    できる
    1.06
    ടുന്ന
    1.06
    もう少し
    1.05
    わざ
    1.03
    毎日
    1.02
    しない
    1.01
    Activations Density 0.174%

    No Known Activations