© 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. 8597
    Prev
    Next
    INDEX
    Explanations

    life, replacement, value, good, knight, structures, night

    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
    aqs
    1.53
    iš
    1.51
    ej
    1.47
    ה
    1.46
    ection
    1.44
    ele
    1.43
    iap
    1.42
     täglich
    1.42
    eine
    1.41
    ea
    1.40
    POSITIVE LOGITS
    并不
    1.70
    ங்களைப்
    1.69
    𝓷
    1.68
    𝓵
    1.68
    纤维
    1.66
    𝓸
    1.63
    𝓼
    1.61
    Ν
    1.60
    𝓻
    1.58
    很好
    1.57
    Activations Density 0.001%

    No Known Activations