© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2530
    Prev
    Next
    INDEX
    Explanations

    categorized lists

    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_65k_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
     nevo
    1.54
     pass
    1.43
     formular
    1.41
     motors
    1.37
     ab
    1.33
    ྕ
    1.31
    ০
    1.30
    vorschau
    1.29
    ில்
    1.29
    ం
    1.28
    POSITIVE LOGITS
    ⁢</
    3.10
    ‖</
    2.46
    ⁡</
    2.31
    ∂</
    2.18
    AppDesigner
    2.09
    ﻳ
    2.02
    يم
    1.90
    ير
    1.79
    Oh
    1.72
    </img>
    1.72
    Activations Density 0.028%

    No Known Activations