© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 2527
    Prev
    Next
    INDEX
    Explanations

    abstract relationships

    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
    ল্প
    1.15
    Facet
    1.14
    RC
    1.10
    rfc
    1.09
    祯
    1.03
    ယ်
    1.03
    ethical
    1.03
    iteks
    1.02
    цвет
    1.00
    আয়
    1.00
    POSITIVE LOGITS
    對方
    1.20
    敵人
    1.15
     enemy
    1.14
    敌
    1.10
    敌人
    1.10
     opponent
    1.07
     rivals
    1.06
     foes
    1.06
     enemies
    1.05
     opponents
    1.03
    Activations Density 0.709%

    No Known Activations